SimpleTool-VLM-FP8 / tensor_audit.json
Cialtion's picture
Upload FP8 Qwen3-VL-4B SimpleTool checkpoint
c052f27 verified
Raw History Blame Contribute Delete
366 kB
{
"passed": true,
"scheme": "fp8",
"coverage": {
"targets": [
"model.language_model.layers.0.mlp.down_proj",
"model.language_model.layers.0.mlp.gate_proj",
"model.language_model.layers.0.mlp.up_proj",
"model.language_model.layers.0.self_attn.k_proj",
"model.language_model.layers.0.self_attn.o_proj",
"model.language_model.layers.0.self_attn.q_proj",
"model.language_model.layers.0.self_attn.v_proj",
"model.language_model.layers.1.mlp.down_proj",
"model.language_model.layers.1.mlp.gate_proj",
"model.language_model.layers.1.mlp.up_proj",
"model.language_model.layers.1.self_attn.k_proj",
"model.language_model.layers.1.self_attn.o_proj",
"model.language_model.layers.1.self_attn.q_proj",
"model.language_model.layers.1.self_attn.v_proj",
"model.language_model.layers.10.mlp.down_proj",
"model.language_model.layers.10.mlp.gate_proj",
"model.language_model.layers.10.mlp.up_proj",
"model.language_model.layers.10.self_attn.k_proj",
"model.language_model.layers.10.self_attn.o_proj",
"model.language_model.layers.10.self_attn.q_proj",
"model.language_model.layers.10.self_attn.v_proj",
"model.language_model.layers.11.mlp.down_proj",
"model.language_model.layers.11.mlp.gate_proj",
"model.language_model.layers.11.mlp.up_proj",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.12.mlp.down_proj",
"model.language_model.layers.12.mlp.gate_proj",
"model.language_model.layers.12.mlp.up_proj",
"model.language_model.layers.12.self_attn.k_proj",
"model.language_model.layers.12.self_attn.o_proj",
"model.language_model.layers.12.self_attn.q_proj",
"model.language_model.layers.12.self_attn.v_proj",
"model.language_model.layers.13.mlp.down_proj",
"model.language_model.layers.13.mlp.gate_proj",
"model.language_model.layers.13.mlp.up_proj",
"model.language_model.layers.13.self_attn.k_proj",
"model.language_model.layers.13.self_attn.o_proj",
"model.language_model.layers.13.self_attn.q_proj",
"model.language_model.layers.13.self_attn.v_proj",
"model.language_model.layers.14.mlp.down_proj",
"model.language_model.layers.14.mlp.gate_proj",
"model.language_model.layers.14.mlp.up_proj",
"model.language_model.layers.14.self_attn.k_proj",
"model.language_model.layers.14.self_attn.o_proj",
"model.language_model.layers.14.self_attn.q_proj",
"model.language_model.layers.14.self_attn.v_proj",
"model.language_model.layers.15.mlp.down_proj",
"model.language_model.layers.15.mlp.gate_proj",
"model.language_model.layers.15.mlp.up_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.16.mlp.down_proj",
"model.language_model.layers.16.mlp.gate_proj",
"model.language_model.layers.16.mlp.up_proj",
"model.language_model.layers.16.self_attn.k_proj",
"model.language_model.layers.16.self_attn.o_proj",
"model.language_model.layers.16.self_attn.q_proj",
"model.language_model.layers.16.self_attn.v_proj",
"model.language_model.layers.17.mlp.down_proj",
"model.language_model.layers.17.mlp.gate_proj",
"model.language_model.layers.17.mlp.up_proj",
"model.language_model.layers.17.self_attn.k_proj",
"model.language_model.layers.17.self_attn.o_proj",
"model.language_model.layers.17.self_attn.q_proj",
"model.language_model.layers.17.self_attn.v_proj",
"model.language_model.layers.18.mlp.down_proj",
"model.language_model.layers.18.mlp.gate_proj",
"model.language_model.layers.18.mlp.up_proj",
"model.language_model.layers.18.self_attn.k_proj",
"model.language_model.layers.18.self_attn.o_proj",
"model.language_model.layers.18.self_attn.q_proj",
"model.language_model.layers.18.self_attn.v_proj",
"model.language_model.layers.19.mlp.down_proj",
"model.language_model.layers.19.mlp.gate_proj",
"model.language_model.layers.19.mlp.up_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.2.mlp.down_proj",
"model.language_model.layers.2.mlp.gate_proj",
"model.language_model.layers.2.mlp.up_proj",
"model.language_model.layers.2.self_attn.k_proj",
"model.language_model.layers.2.self_attn.o_proj",
"model.language_model.layers.2.self_attn.q_proj",
"model.language_model.layers.2.self_attn.v_proj",
"model.language_model.layers.20.mlp.down_proj",
"model.language_model.layers.20.mlp.gate_proj",
"model.language_model.layers.20.mlp.up_proj",
"model.language_model.layers.20.self_attn.k_proj",
"model.language_model.layers.20.self_attn.o_proj",
"model.language_model.layers.20.self_attn.q_proj",
"model.language_model.layers.20.self_attn.v_proj",
"model.language_model.layers.21.mlp.down_proj",
"model.language_model.layers.21.mlp.gate_proj",
"model.language_model.layers.21.mlp.up_proj",
"model.language_model.layers.21.self_attn.k_proj",
"model.language_model.layers.21.self_attn.o_proj",
"model.language_model.layers.21.self_attn.q_proj",
"model.language_model.layers.21.self_attn.v_proj",
"model.language_model.layers.22.mlp.down_proj",
"model.language_model.layers.22.mlp.gate_proj",
"model.language_model.layers.22.mlp.up_proj",
"model.language_model.layers.22.self_attn.k_proj",
"model.language_model.layers.22.self_attn.o_proj",
"model.language_model.layers.22.self_attn.q_proj",
"model.language_model.layers.22.self_attn.v_proj",
"model.language_model.layers.23.mlp.down_proj",
"model.language_model.layers.23.mlp.gate_proj",
"model.language_model.layers.23.mlp.up_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.24.mlp.down_proj",
"model.language_model.layers.24.mlp.gate_proj",
"model.language_model.layers.24.mlp.up_proj",
"model.language_model.layers.24.self_attn.k_proj",
"model.language_model.layers.24.self_attn.o_proj",
"model.language_model.layers.24.self_attn.q_proj",
"model.language_model.layers.24.self_attn.v_proj",
"model.language_model.layers.25.mlp.down_proj",
"model.language_model.layers.25.mlp.gate_proj",
"model.language_model.layers.25.mlp.up_proj",
"model.language_model.layers.25.self_attn.k_proj",
"model.language_model.layers.25.self_attn.o_proj",
"model.language_model.layers.25.self_attn.q_proj",
"model.language_model.layers.25.self_attn.v_proj",
"model.language_model.layers.26.mlp.down_proj",
"model.language_model.layers.26.mlp.gate_proj",
"model.language_model.layers.26.mlp.up_proj",
"model.language_model.layers.26.self_attn.k_proj",
"model.language_model.layers.26.self_attn.o_proj",
"model.language_model.layers.26.self_attn.q_proj",
"model.language_model.layers.26.self_attn.v_proj",
"model.language_model.layers.27.mlp.down_proj",
"model.language_model.layers.27.mlp.gate_proj",
"model.language_model.layers.27.mlp.up_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.28.mlp.down_proj",
"model.language_model.layers.28.mlp.gate_proj",
"model.language_model.layers.28.mlp.up_proj",
"model.language_model.layers.28.self_attn.k_proj",
"model.language_model.layers.28.self_attn.o_proj",
"model.language_model.layers.28.self_attn.q_proj",
"model.language_model.layers.28.self_attn.v_proj",
"model.language_model.layers.29.mlp.down_proj",
"model.language_model.layers.29.mlp.gate_proj",
"model.language_model.layers.29.mlp.up_proj",
"model.language_model.layers.29.self_attn.k_proj",
"model.language_model.layers.29.self_attn.o_proj",
"model.language_model.layers.29.self_attn.q_proj",
"model.language_model.layers.29.self_attn.v_proj",
"model.language_model.layers.3.mlp.down_proj",
"model.language_model.layers.3.mlp.gate_proj",
"model.language_model.layers.3.mlp.up_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.30.mlp.down_proj",
"model.language_model.layers.30.mlp.gate_proj",
"model.language_model.layers.30.mlp.up_proj",
"model.language_model.layers.30.self_attn.k_proj",
"model.language_model.layers.30.self_attn.o_proj",
"model.language_model.layers.30.self_attn.q_proj",
"model.language_model.layers.30.self_attn.v_proj",
"model.language_model.layers.31.mlp.down_proj",
"model.language_model.layers.31.mlp.gate_proj",
"model.language_model.layers.31.mlp.up_proj",
"model.language_model.layers.31.self_attn.k_proj",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.31.self_attn.q_proj",
"model.language_model.layers.31.self_attn.v_proj",
"model.language_model.layers.32.mlp.down_proj",
"model.language_model.layers.32.mlp.gate_proj",
"model.language_model.layers.32.mlp.up_proj",
"model.language_model.layers.32.self_attn.k_proj",
"model.language_model.layers.32.self_attn.o_proj",
"model.language_model.layers.32.self_attn.q_proj",
"model.language_model.layers.32.self_attn.v_proj",
"model.language_model.layers.33.mlp.down_proj",
"model.language_model.layers.33.mlp.gate_proj",
"model.language_model.layers.33.mlp.up_proj",
"model.language_model.layers.33.self_attn.k_proj",
"model.language_model.layers.33.self_attn.o_proj",
"model.language_model.layers.33.self_attn.q_proj",
"model.language_model.layers.33.self_attn.v_proj",
"model.language_model.layers.34.mlp.down_proj",
"model.language_model.layers.34.mlp.gate_proj",
"model.language_model.layers.34.mlp.up_proj",
"model.language_model.layers.34.self_attn.k_proj",
"model.language_model.layers.34.self_attn.o_proj",
"model.language_model.layers.34.self_attn.q_proj",
"model.language_model.layers.34.self_attn.v_proj",
"model.language_model.layers.35.mlp.down_proj",
"model.language_model.layers.35.mlp.gate_proj",
"model.language_model.layers.35.mlp.up_proj",
"model.language_model.layers.35.self_attn.k_proj",
"model.language_model.layers.35.self_attn.o_proj",
"model.language_model.layers.35.self_attn.q_proj",
"model.language_model.layers.35.self_attn.v_proj",
"model.language_model.layers.4.mlp.down_proj",
"model.language_model.layers.4.mlp.gate_proj",
"model.language_model.layers.4.mlp.up_proj",
"model.language_model.layers.4.self_attn.k_proj",
"model.language_model.layers.4.self_attn.o_proj",
"model.language_model.layers.4.self_attn.q_proj",
"model.language_model.layers.4.self_attn.v_proj",
"model.language_model.layers.5.mlp.down_proj",
"model.language_model.layers.5.mlp.gate_proj",
"model.language_model.layers.5.mlp.up_proj",
"model.language_model.layers.5.self_attn.k_proj",
"model.language_model.layers.5.self_attn.o_proj",
"model.language_model.layers.5.self_attn.q_proj",
"model.language_model.layers.5.self_attn.v_proj",
"model.language_model.layers.6.mlp.down_proj",
"model.language_model.layers.6.mlp.gate_proj",
"model.language_model.layers.6.mlp.up_proj",
"model.language_model.layers.6.self_attn.k_proj",
"model.language_model.layers.6.self_attn.o_proj",
"model.language_model.layers.6.self_attn.q_proj",
"model.language_model.layers.6.self_attn.v_proj",
"model.language_model.layers.7.mlp.down_proj",
"model.language_model.layers.7.mlp.gate_proj",
"model.language_model.layers.7.mlp.up_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.v_proj",
"model.language_model.layers.8.mlp.down_proj",
"model.language_model.layers.8.mlp.gate_proj",
"model.language_model.layers.8.mlp.up_proj",
"model.language_model.layers.8.self_attn.k_proj",
"model.language_model.layers.8.self_attn.o_proj",
"model.language_model.layers.8.self_attn.q_proj",
"model.language_model.layers.8.self_attn.v_proj",
"model.language_model.layers.9.mlp.down_proj",
"model.language_model.layers.9.mlp.gate_proj",
"model.language_model.layers.9.mlp.up_proj",
"model.language_model.layers.9.self_attn.k_proj",
"model.language_model.layers.9.self_attn.o_proj",
"model.language_model.layers.9.self_attn.q_proj",
"model.language_model.layers.9.self_attn.v_proj"
],
"original_parameters": 4825491968,
"quantized_weight_parameters": 3633315840,
"quantized_parameter_fraction": 0.7529420552544996,
"preserved_bf16_parameters": 1192176128,
"tensor_count": 714,
"dtypes": {
"BF16": 714
}
},
"storage_tensor_dtypes": {
"BF16": 714,
"F8_E4M3": 252
},
"storage_bytes_by_dtype": {
"BF16": 2386564096,
"F8_E4M3": 3633315840
},
"preserved_tensor_hashes": [
{
"name": "lm_head.weight",
"sha256": "9ac2e2a7bf6f81bad63f0d63e0d0d64e55056051061890336814491da993e272"
},
{
"name": "model.language_model.embed_tokens.weight",
"sha256": "f5aaeaab90ae4f078174492876a525c9d74d9cb3ab54df9b55603bbec2c98630"
},
{
"name": "model.language_model.layers.0.input_layernorm.weight",
"sha256": "a06277a2724034a966ccb331fdd94d5bbff4b3a1e9dd6144fa9a1315a0550034"
},
{
"name": "model.language_model.layers.0.post_attention_layernorm.weight",
"sha256": "45ec770644ec203f2fe3ceea92f91659abe716f08a6269ea21149884709ade43"
},
{
"name": "model.language_model.layers.0.self_attn.k_norm.weight",
"sha256": "aa3ca7fbbcd37f0d0a73c22744118bf4226950a89ada3915c640a857b5952cd3"
},
{
"name": "model.language_model.layers.0.self_attn.q_norm.weight",
"sha256": "ff411b343de643975b739631e9140ebce4f27268a9e605e7ca49cc994f209ec4"
},
{
"name": "model.language_model.layers.1.input_layernorm.weight",
"sha256": "f0b6f9fae8016ea26dda8221e19b1570b0e72eac28ea21284d94d3fdbafb72c5"
},
{
"name": "model.language_model.layers.1.post_attention_layernorm.weight",
"sha256": "04a6ea58c8918eccdbe6f510568e1f10500a1811fe62a621a86929c10c5ab216"
},
{
"name": "model.language_model.layers.1.self_attn.k_norm.weight",
"sha256": "f55faeba76b144f712b6b94382c3b356ac235b8647f0480c76a68a9d56ed70dd"
},
{
"name": "model.language_model.layers.1.self_attn.q_norm.weight",
"sha256": "f45fcb924368806da6391c717fdb6481c817e38968d0397358452542d9322ed3"
},
{
"name": "model.language_model.layers.10.input_layernorm.weight",
"sha256": "f8c2da45ccca2f6f680c5b7184ecb57771b3b0c331ba98993577b94187320439"
},
{
"name": "model.language_model.layers.10.post_attention_layernorm.weight",
"sha256": "60f3324bfb75d74a4c883d459e188b54901ff486cedd54e364c7d4ba0efc695d"
},
{
"name": "model.language_model.layers.10.self_attn.k_norm.weight",
"sha256": "305bc11cb3da4b8ef9dd14c5ac047292e2b7f1f5c1da67aa5f961b28c1909a1d"
},
{
"name": "model.language_model.layers.10.self_attn.q_norm.weight",
"sha256": "d54b0af2ee3f945d61f05252cdb16717c5862b2cc955f2e9a5b8daaf5d0382c2"
},
{
"name": "model.language_model.layers.11.input_layernorm.weight",
"sha256": "cfacd4d29f0b5108c9b093cacc5952173956302345c87cc1e14fc1e56fe7e6db"
},
{
"name": "model.language_model.layers.11.post_attention_layernorm.weight",
"sha256": "b04fd8ac527aaab0a28b0d64d67ab28dd56a90c2562c341208c55e5883141f41"
},
{
"name": "model.language_model.layers.11.self_attn.k_norm.weight",
"sha256": "6604780d1df1a7396eb1bcc546752d1209314ba3abcc913386903b4984efcc82"
},
{
"name": "model.language_model.layers.11.self_attn.q_norm.weight",
"sha256": "a55e87d5eca0607b9c3d9e52cff7ce975f4104dd4cb73b1380ecd47d9a07c809"
},
{
"name": "model.language_model.layers.12.input_layernorm.weight",
"sha256": "74261a28df4799dfddfec02d108604cc96deded9e3bc02441a0491117bfe00b4"
},
{
"name": "model.language_model.layers.2.input_layernorm.weight",
"sha256": "0eeed82b1d112f9eb8059ee5a6a11629acc82c6f17d9d28c07cb0467f4fb9af1"
},
{
"name": "model.language_model.layers.2.post_attention_layernorm.weight",
"sha256": "49cfc4473f10ce175685e557039fea89fcd568d3c84abd9cf528a825b3febb63"
},
{
"name": "model.language_model.layers.2.self_attn.k_norm.weight",
"sha256": "8229b224a57729244f100046e167efaf9dd1f6113c8ccc7d34789e4c11b6fd4a"
},
{
"name": "model.language_model.layers.2.self_attn.q_norm.weight",
"sha256": "4813a0ff852f7ec610d319651bcd3b934c55ac1ae621ba4333ea749e211aa248"
},
{
"name": "model.language_model.layers.3.input_layernorm.weight",
"sha256": "582659fb73903e843bd9081d45c888a6898d57f6dfe273f126229ef15bf3a9b8"
},
{
"name": "model.language_model.layers.3.post_attention_layernorm.weight",
"sha256": "dff99bb48f43bfaf12cac723b493df6bd6347f5b3acff22095182cf687c4ab08"
},
{
"name": "model.language_model.layers.3.self_attn.k_norm.weight",
"sha256": "f9aab5c59fb065238df141dd469f54d6dd6074f84eb4e6582bd1b60b1ec78c72"
},
{
"name": "model.language_model.layers.3.self_attn.q_norm.weight",
"sha256": "b01b96d7f8025611f8eb82ddb9c3a5efa5f44905366e2bceb86039de884f0312"
},
{
"name": "model.language_model.layers.4.input_layernorm.weight",
"sha256": "9667c70d292c9e8130f35d54d5d5c8ffdd564773c3e7d9f36aef3d3611c048c4"
},
{
"name": "model.language_model.layers.4.post_attention_layernorm.weight",
"sha256": "d71a366b4153182fa3f7c7021d32d9ef150808c07215d7915ecae50f24f82b88"
},
{
"name": "model.language_model.layers.4.self_attn.k_norm.weight",
"sha256": "ca28d17d50ddd55a9817a3691fec7015508326dff59d2e5df3169bb4756dc820"
},
{
"name": "model.language_model.layers.4.self_attn.q_norm.weight",
"sha256": "56c8553cff67585ffe89d19c7e808db6d3d8498200afb8c48731c2765f49529b"
},
{
"name": "model.language_model.layers.5.input_layernorm.weight",
"sha256": "dcfacc1f3488623905ccb63a2d7632f8974bd443c696848b1d28ed9f55667243"
},
{
"name": "model.language_model.layers.5.post_attention_layernorm.weight",
"sha256": "f37b1f40b05e128e4a55f83ef1d473ab6669fa624f6882784567021f034429e7"
},
{
"name": "model.language_model.layers.5.self_attn.k_norm.weight",
"sha256": "baf63098a2ed27c0ee75b439c9791fada1da39b01f8857a60efcb3affa0c825a"
},
{
"name": "model.language_model.layers.5.self_attn.q_norm.weight",
"sha256": "b6cc41a3f1f83fe59b783500549a5bf62f2a01f96d7317b776a83a2b1cfede03"
},
{
"name": "model.language_model.layers.6.input_layernorm.weight",
"sha256": "9acd1d942243daa31d01718de34fa01962d5e50bbb68ebc0b6af7ff956780d21"
},
{
"name": "model.language_model.layers.6.post_attention_layernorm.weight",
"sha256": "c52d5aa46fc4cb3f8205650658accf44150a89815cf8ba4eb9eb9deba337a36e"
},
{
"name": "model.language_model.layers.6.self_attn.k_norm.weight",
"sha256": "1a9c8149fbc7e053faa49ccd99759b37351b485baaec1e47cba6677d5283820c"
},
{
"name": "model.language_model.layers.6.self_attn.q_norm.weight",
"sha256": "ef14b53cd0fe1be799cb4667e69d51827236bfa4cfa4277ac912f9962e6026f4"
},
{
"name": "model.language_model.layers.7.input_layernorm.weight",
"sha256": "eafb74c06e3c7b4d1bcde2883f22adb4f91f8ecc507d94fe7e9867bcf8db5d62"
},
{
"name": "model.language_model.layers.7.post_attention_layernorm.weight",
"sha256": "1773511c1ea615601ab24816276325378883ead6288bd484e9819e1716cc1a6d"
},
{
"name": "model.language_model.layers.7.self_attn.k_norm.weight",
"sha256": "47692c6b93d1b4081054e3315987f24ea4c96a4a003322da0274a1ebb257d5b5"
},
{
"name": "model.language_model.layers.7.self_attn.q_norm.weight",
"sha256": "5e57baec6f17e91fac2c9dc83290a7b9509ea938daa66cef03134f82d82f63d6"
},
{
"name": "model.language_model.layers.8.input_layernorm.weight",
"sha256": "3ff63433cf05a3e4a55f9b61924181680166b6f155c81923a142226246c900e0"
},
{
"name": "model.language_model.layers.8.post_attention_layernorm.weight",
"sha256": "a311cd31f774533003d80f96ec1c9a8ef9aa542d827cc7360f7bc05c12d6515d"
},
{
"name": "model.language_model.layers.8.self_attn.k_norm.weight",
"sha256": "e6d177c6c83b8330be2f07b1a99550564eb8af86e812c61a6cd0454867215606"
},
{
"name": "model.language_model.layers.8.self_attn.q_norm.weight",
"sha256": "f684e269ebfab15b3f31ed6385cb0be286e74820bb50949ee5e0735ff7f0297f"
},
{
"name": "model.language_model.layers.9.input_layernorm.weight",
"sha256": "3f4299e99da41f16cdd3b9a70906fd8c2419afeaf2b9f32439e85bdd22e970fe"
},
{
"name": "model.language_model.layers.9.post_attention_layernorm.weight",
"sha256": "1b836a52c002fd657410c5b488e47dbfb8f24429e854414d627cada5f3839bb6"
},
{
"name": "model.language_model.layers.9.self_attn.k_norm.weight",
"sha256": "882e8a32b2a1666771177b05cfbd17226fc20c383edafd9a0ecdf95c8b646681"
},
{
"name": "model.language_model.layers.9.self_attn.q_norm.weight",
"sha256": "f61182f35354352d56601c25dbd6d2e2be416c4605bdc728c975b6c08b802237"
},
{
"name": "model.language_model.layers.12.post_attention_layernorm.weight",
"sha256": "a56475c56f4cbc33417bbae58af0f128d6357eb2ae4c6acf0bd482c8c281d40f"
},
{
"name": "model.language_model.layers.12.self_attn.k_norm.weight",
"sha256": "5e44da8b368845b4cd449990a5c95b17452cb2f5d8526181a933eacacece8fce"
},
{
"name": "model.language_model.layers.12.self_attn.q_norm.weight",
"sha256": "57712b8a54002657409d12e6e6a9876105bf32633a244bcb2ab8e07f7b8beffb"
},
{
"name": "model.language_model.layers.13.input_layernorm.weight",
"sha256": "308ca42bceb2fcbeb19f5e52390b203c9ad570357e70a0ad1cd134319089877b"
},
{
"name": "model.language_model.layers.13.post_attention_layernorm.weight",
"sha256": "83b1a823787025a5a7d40d66bebbc7bf572ec217c6892750e6620217c7c5bde7"
},
{
"name": "model.language_model.layers.13.self_attn.k_norm.weight",
"sha256": "c749035725959c0a09b7ea09c6bb03bb481030512f2257dc7837dfd72a0f313d"
},
{
"name": "model.language_model.layers.13.self_attn.q_norm.weight",
"sha256": "25cf1e2cc0719d6acc2d383d59a3c34017bde69401c4d6ea8d3c1cf7ef704d0e"
},
{
"name": "model.language_model.layers.14.input_layernorm.weight",
"sha256": "a0e2378f01bbdb98c4347acb9e3a7df9b5f6d2e8e937d5692a87336c272e67e9"
},
{
"name": "model.language_model.layers.14.post_attention_layernorm.weight",
"sha256": "e9b3bff08e3958dd5c6d11147ae7e678189e112f89397609f65b958901b12208"
},
{
"name": "model.language_model.layers.14.self_attn.k_norm.weight",
"sha256": "a295a90ef05067dc9cf15467845d4bfe96cc0ab06bb5bd4388c3b5133da1d1f1"
},
{
"name": "model.language_model.layers.14.self_attn.q_norm.weight",
"sha256": "96c80400a980dfdf54be86faeaf35d840c293f8572b8b776eab8689a1eaba9c3"
},
{
"name": "model.language_model.layers.15.input_layernorm.weight",
"sha256": "51dc26129cc1404ddf3f7a78b8ec9ae6744e88acafad93e6b1b716587091536d"
},
{
"name": "model.language_model.layers.15.post_attention_layernorm.weight",
"sha256": "fd133c359225016a4e6a4fb197acc904cfe5ff517dcd291bd31bfe2ce32f347b"
},
{
"name": "model.language_model.layers.15.self_attn.k_norm.weight",
"sha256": "129d971d2b70305a92c32a48e6fdd570a29991ae5dce34530eca55479850fb1c"
},
{
"name": "model.language_model.layers.15.self_attn.q_norm.weight",
"sha256": "bcf5046a1405830c0fc5518cb5ed062cd688f696ac18d6c2cc57caad80ba4e14"
},
{
"name": "model.language_model.layers.16.input_layernorm.weight",
"sha256": "a512b97ae95ce9d61bfd8d45605b8b327b47ee7185289804a983de5c502add99"
},
{
"name": "model.language_model.layers.16.post_attention_layernorm.weight",
"sha256": "96862d097aac31663e9f32e513923795bc02b429666a6190eb5303f1e29ecdcd"
},
{
"name": "model.language_model.layers.16.self_attn.k_norm.weight",
"sha256": "4700d24f39e08f8a75fb06a9c0c7651fdf3f771a4014035c66bc043f43de680a"
},
{
"name": "model.language_model.layers.16.self_attn.q_norm.weight",
"sha256": "e082f05d85b462596406d8d362674eff8dd173e77be5d426ce08f9f0dc5f5d58"
},
{
"name": "model.language_model.layers.17.input_layernorm.weight",
"sha256": "16e5c46ae4133745a03bedc22b97523fb1f1f5364e7d5b1c6a31758c65ca5105"
},
{
"name": "model.language_model.layers.17.post_attention_layernorm.weight",
"sha256": "34fbce23a08e85df36bd37ddb84c82d2c2dc526d46c1ca89fe45369d8d8adbe8"
},
{
"name": "model.language_model.layers.17.self_attn.k_norm.weight",
"sha256": "3ca82e293a743c3fe928ab750b1ce7eed181a4b9ee4c5d9db30bc71a21e19891"
},
{
"name": "model.language_model.layers.17.self_attn.q_norm.weight",
"sha256": "a27bdd05ce857c930346595071f75d6a6a5d63c3afd65faba234f1b4c5c34322"
},
{
"name": "model.language_model.layers.18.input_layernorm.weight",
"sha256": "7a9792aa19bc2b108cc16b38c6fa0100d3b8f3be7eefd11cfe4a5b0cc03ce918"
},
{
"name": "model.language_model.layers.18.post_attention_layernorm.weight",
"sha256": "f10aef7d576ed1bc0b1d57782c5ee2802306d1c293d7017602a7750b837dba98"
},
{
"name": "model.language_model.layers.18.self_attn.k_norm.weight",
"sha256": "a37d0db4743806c70d955795851e6a1cb722903a79b62bb989a5ee94019988c1"
},
{
"name": "model.language_model.layers.18.self_attn.q_norm.weight",
"sha256": "36ac4ddc43fc5c55001e394d22dbcfde37c416bd57d97a29941f24f072f2b4ec"
},
{
"name": "model.language_model.layers.19.input_layernorm.weight",
"sha256": "d0b732324e3348adb9057acf7fad9bde0d3afa919807e20f8f1041bad59c6721"
},
{
"name": "model.language_model.layers.19.post_attention_layernorm.weight",
"sha256": "1fdba3e55eb265d58f6d5b0c8be7d3d4f91d9a440a1c5966bb87cf903eba412e"
},
{
"name": "model.language_model.layers.19.self_attn.k_norm.weight",
"sha256": "433e247e9158bc3b76e9f2498f7a9f337b760311d71a6381684cd00c1ef94757"
},
{
"name": "model.language_model.layers.19.self_attn.q_norm.weight",
"sha256": "a3b68a801f4b72c2019ba09f2ee4b2b4548f9fd0cd631593ffb088464d6105b7"
},
{
"name": "model.language_model.layers.20.input_layernorm.weight",
"sha256": "7610ced9597357d4fc8259887f6fc9bee33658d7e069d72cbb644e151bfc0088"
},
{
"name": "model.language_model.layers.20.post_attention_layernorm.weight",
"sha256": "620c83b104c5550c05b346036bac3f2cb0ac831b78fa7b5985712159576fc867"
},
{
"name": "model.language_model.layers.20.self_attn.k_norm.weight",
"sha256": "6a316c6f03c68b56a7236e065d8c0f26d9f160bcd1dd90424252473140972e92"
},
{
"name": "model.language_model.layers.20.self_attn.q_norm.weight",
"sha256": "dea579095af43a4e01d9c92ee14a0ce2d990cf027aba2e6f26a18608c5ab7348"
},
{
"name": "model.language_model.layers.21.input_layernorm.weight",
"sha256": "4e5aabadeb9f5775f7bc77ac65830a2a417d6d7422bf6a4e76fcac593f3507cc"
},
{
"name": "model.language_model.layers.21.post_attention_layernorm.weight",
"sha256": "52c751a32519c452dd79c01801862157d620a3e6b04ae17a5637f54a10612e02"
},
{
"name": "model.language_model.layers.21.self_attn.k_norm.weight",
"sha256": "b20b256c10fb07975ad3327daaf08cb61a0f18ae883bc562b4a562621d2c9055"
},
{
"name": "model.language_model.layers.21.self_attn.q_norm.weight",
"sha256": "24a859cbee477119f3d6f00a36591b1ecff09f8dea7a879e0f7e63cf06048ee9"
},
{
"name": "model.language_model.layers.22.input_layernorm.weight",
"sha256": "470293ea1cb88830f22504c7f10f1e4e2b7161608646bc13bc68f941f612bf06"
},
{
"name": "model.language_model.layers.22.post_attention_layernorm.weight",
"sha256": "31f8ca35e9bf624089cc4629deafc10c22cfda75b0357d513fac47a17d8bf0a7"
},
{
"name": "model.language_model.layers.22.self_attn.k_norm.weight",
"sha256": "0dffc0c3fc4f4dacd1f1d0530d8a280f25a2ecda895a979690a7c99fd4edfd7c"
},
{
"name": "model.language_model.layers.22.self_attn.q_norm.weight",
"sha256": "a63edeab3da13ac771166e1a120fef0c9cd890553fed425e66fb7800d34e44b1"
},
{
"name": "model.language_model.layers.23.input_layernorm.weight",
"sha256": "ed4a775a933488a66de9c4bced6a32f48a2ec40080966530e2935ba9fa8fd137"
},
{
"name": "model.language_model.layers.23.post_attention_layernorm.weight",
"sha256": "3aec221c7c7eaae0943af04e7072f870b29ba7ae5aaa78d6e42c8b10ade959fb"
},
{
"name": "model.language_model.layers.23.self_attn.k_norm.weight",
"sha256": "05df1e5ae04792d19673dbdd1f8c612e53bb5e2400d6e13346e0f02f42c8985f"
},
{
"name": "model.language_model.layers.23.self_attn.q_norm.weight",
"sha256": "afafb183c6984039416bea9348daac75947d6030c39aa7aebf2317dcf95bb998"
},
{
"name": "model.language_model.layers.24.input_layernorm.weight",
"sha256": "2d7c6bdf55e295a796efd351c0317af90a494866ad2db29da10fa8808c653e16"
},
{
"name": "model.language_model.layers.24.post_attention_layernorm.weight",
"sha256": "40fd9f81530c7569ce92bcc8536086d3c0140399582a8d9440b1ad680c422610"
},
{
"name": "model.language_model.layers.24.self_attn.k_norm.weight",
"sha256": "d684fb2c7840551ce81668581c7ea6248bd3686007f88397fb00bf130617055b"
},
{
"name": "model.language_model.layers.24.self_attn.q_norm.weight",
"sha256": "333c5d525d7a4d39754bd605b016af1464147b7bf028fa04892c4c6c2438d622"
},
{
"name": "model.language_model.layers.25.input_layernorm.weight",
"sha256": "a8d218fa27a5b6fa72acaaab3c8147445a43e1cd10fac778d1180857e6a45dea"
},
{
"name": "model.language_model.layers.25.post_attention_layernorm.weight",
"sha256": "41d1eaa0dae723792c86b38bc516ea161eaaed92d355d6c3b9bab50efca952b1"
},
{
"name": "model.language_model.layers.25.self_attn.k_norm.weight",
"sha256": "e4e2a9e8131bb546c96866ff412dff32c33e89359ef0c9410a1f5bb2e58e3c47"
},
{
"name": "model.language_model.layers.25.self_attn.q_norm.weight",
"sha256": "9bc0e87b169d49bb0070e07e6cf2b4b9cd9be0c4c1bf1bfc2b1fc5bc0ab8807a"
},
{
"name": "model.language_model.layers.26.input_layernorm.weight",
"sha256": "f4f270246c7fcc016f6eea8c2353897f999fd2be05eef75588878b48405c87d0"
},
{
"name": "model.language_model.layers.26.post_attention_layernorm.weight",
"sha256": "3ca2bd525f6b2ed426abe3544180975c8f4e64a02911723b729cc88ac119ae40"
},
{
"name": "model.language_model.layers.26.self_attn.k_norm.weight",
"sha256": "06a5041f7a00123c8808b1f3b627ca10abe0a8ce3720686ccbae38ddedc51438"
},
{
"name": "model.language_model.layers.26.self_attn.q_norm.weight",
"sha256": "6328767359760794d9193d1061cc8821bc73caf17415c0e28e47ce397afac073"
},
{
"name": "model.language_model.layers.27.input_layernorm.weight",
"sha256": "09dac18f0a66dd39b9e44e198557b3527fb41f72b4a6664f7bfe14c32e416dee"
},
{
"name": "model.language_model.layers.27.post_attention_layernorm.weight",
"sha256": "b81c6ad07923322340604e2bc13a1ee168ec579abff0732161d5a46faf0cd203"
},
{
"name": "model.language_model.layers.27.self_attn.k_norm.weight",
"sha256": "5e455c6442568b5d9e659843d54dfab7ed04846d43a098763877c34196603ff6"
},
{
"name": "model.language_model.layers.27.self_attn.q_norm.weight",
"sha256": "f89b4f7e3486a2402f6e1808e7912a7117d9013e6033983aba2c075698931657"
},
{
"name": "model.language_model.layers.28.input_layernorm.weight",
"sha256": "93dbe96490366724cf40336e8201d6dd102f2ca29f9125f00935bcb84577638f"
},
{
"name": "model.language_model.layers.28.post_attention_layernorm.weight",
"sha256": "656f8d674dab959101e94b3fb7735eb34e936741d4e17d2c93c765cd0d1ad9d9"
},
{
"name": "model.language_model.layers.28.self_attn.k_norm.weight",
"sha256": "ccfbd385674496d3535f0beeb5b2e8c8b894ec69a337968950903a31069fb40f"
},
{
"name": "model.language_model.layers.28.self_attn.q_norm.weight",
"sha256": "8bff75f822e61a4ce906998dab1edc8cf9db6728d98066ffd95073079f7fdee4"
},
{
"name": "model.language_model.layers.29.input_layernorm.weight",
"sha256": "9c1f9d70f77d5cd6aa8841f1c3145f639c9d23fc2a64fec738319134607526f7"
},
{
"name": "model.language_model.layers.29.post_attention_layernorm.weight",
"sha256": "ba2ccca7276783878f232546e8125c52aa8cc44def57f163e88be6e94724bd48"
},
{
"name": "model.language_model.layers.29.self_attn.k_norm.weight",
"sha256": "065130b13e2f3150665a92e6cc07fe713adbe894e7375b9f5f2caf5496f093d9"
},
{
"name": "model.language_model.layers.29.self_attn.q_norm.weight",
"sha256": "624fd119ccd540b8e60bc0336c855a1067679ee73a887e502a169d59671f6ca2"
},
{
"name": "model.language_model.layers.30.input_layernorm.weight",
"sha256": "8f69ecd26e8ef1121cf891687dd46e357bea2a5206e5eae51099e3cddd112b31"
},
{
"name": "model.language_model.layers.30.post_attention_layernorm.weight",
"sha256": "e7002063bb737880c10bd142e0320164c83875e941629c5d7102448312bd59b9"
},
{
"name": "model.language_model.layers.30.self_attn.k_norm.weight",
"sha256": "98b109d20a58765799f8c2de8ca3c40bcd31d497ed3490d68ec75cc4341686d8"
},
{
"name": "model.language_model.layers.30.self_attn.q_norm.weight",
"sha256": "f9874be81b284d9d34a237a15f4cd1b66da8132bf1549b5f3df301ba21866615"
},
{
"name": "model.language_model.layers.31.input_layernorm.weight",
"sha256": "af99daf3ad082cac8de4e94cb4a3e3c01068358383e4e549e0d75d4ffbf2fe59"
},
{
"name": "model.language_model.layers.31.post_attention_layernorm.weight",
"sha256": "ae287b1b990e6db8acf7a4a39089aa1ef236c6bd4523b5f5e739b821ab01a1d3"
},
{
"name": "model.language_model.layers.31.self_attn.k_norm.weight",
"sha256": "5ff58f95523e506bf186d18ee10070415d98d9e6f8152ea0a1af0d3017ed82d2"
},
{
"name": "model.language_model.layers.31.self_attn.q_norm.weight",
"sha256": "2cad08c509e915c38bb614d86b7129b03f5f0d2ed8444b598009aab53a419a0a"
},
{
"name": "model.language_model.layers.32.input_layernorm.weight",
"sha256": "7791f82d5d692519f50080ca927d5bbf9edaacb5b10eae5177f3b6e5a209255e"
},
{
"name": "model.language_model.layers.32.post_attention_layernorm.weight",
"sha256": "8fbd81c49bd0261757f71e68759ade0b8a1518651bed35bbb604555d4faf5d58"
},
{
"name": "model.language_model.layers.32.self_attn.k_norm.weight",
"sha256": "0f716332074650b760e30bdbb926f7c53a8ad8cedb82aed5d09f8cbe1765e068"
},
{
"name": "model.language_model.layers.32.self_attn.q_norm.weight",
"sha256": "5ba9c7c18f85aaeab4562e7713fc34ddf3742a1be2d0743d0921f5eac98974fa"
},
{
"name": "model.language_model.layers.33.input_layernorm.weight",
"sha256": "7bee01ffe1a1b1c60299ebfeba8a5b9f9f430b690633d1a5761c0486894e8b76"
},
{
"name": "model.language_model.layers.33.post_attention_layernorm.weight",
"sha256": "2c55fd8615e4f5645e85dc8980dd49493c55459915eb9be52934ab49025fe960"
},
{
"name": "model.language_model.layers.33.self_attn.k_norm.weight",
"sha256": "46e05b757511a01c1e124537625f731c02168766cb6097815029319107a0dfed"
},
{
"name": "model.language_model.layers.33.self_attn.q_norm.weight",
"sha256": "1f4cfba4e96f000f61e300327fae6bdf13911c1cf4d82e98a918e251af758736"
},
{
"name": "model.language_model.layers.34.input_layernorm.weight",
"sha256": "963037a380772d1490f263d2080c288915948f76097c053673d30ad2a3064c5a"
},
{
"name": "model.language_model.layers.34.post_attention_layernorm.weight",
"sha256": "f3ef8f9ee4995eae356b2119655d37cc6ef72ba79fd8156252fa081b55bf8dde"
},
{
"name": "model.language_model.layers.34.self_attn.k_norm.weight",
"sha256": "7d794e1dab1121f0fe6d1fa0c1dcf25fd6faa40389591e216b409c9c4f9e29b8"
},
{
"name": "model.language_model.layers.34.self_attn.q_norm.weight",
"sha256": "040f74a4b84981d772349865f1478ad5933aa88a90224b70c49377d7bc5f3153"
},
{
"name": "model.language_model.layers.35.input_layernorm.weight",
"sha256": "19330a6822fb0b06ecbc169881eee5e9d045fc94a666965a608c314266a7e997"
},
{
"name": "model.language_model.layers.35.post_attention_layernorm.weight",
"sha256": "f886e2e08678ee4265126eb1ade951f4ab58cf451a502fd920b5de182ff00fd5"
},
{
"name": "model.language_model.layers.35.self_attn.k_norm.weight",
"sha256": "aef87d3479e9783ac1bffbe7a99f38b05341109362a51c7f7b00fa58ade36daf"
},
{
"name": "model.language_model.layers.35.self_attn.q_norm.weight",
"sha256": "24905406aeb90a64865577af1c66b2360fc7aef64b897736dbefddbf47a1be74"
},
{
"name": "model.language_model.norm.weight",
"sha256": "59be4927491b995e61ca021ca3d1bddf90bed0f522ec73e9311ebfb5fb8bd9e8"
},
{
"name": "model.visual.blocks.0.attn.proj.bias",
"sha256": "cdc55e466e1ea5feaaa1c15461b33e4eed865230c8c014c2a09e3c001ea5062a"
},
{
"name": "model.visual.blocks.0.attn.proj.weight",
"sha256": "23dd8d3f45f9d5425443c0cfba0ebc8bcd635032786b89414b34d589ac8d6279"
},
{
"name": "model.visual.blocks.0.attn.qkv.bias",
"sha256": "ff2c5023d70b4186f978ee8fb9c5aeb33c954076040fa13ad8aab93ac4e0d5f0"
},
{
"name": "model.visual.blocks.0.attn.qkv.weight",
"sha256": "e0f1bc96064d474c239f7a2e02a60dec9f52ad3e8200977f36f69f7517b46119"
},
{
"name": "model.visual.blocks.0.mlp.linear_fc1.bias",
"sha256": "735a4a481d626b31b02e6df453955d99ef454c300741771a1d7dc86ead378ec7"
},
{
"name": "model.visual.blocks.0.mlp.linear_fc1.weight",
"sha256": "1720c88798b46807ec38b146848c16b663b04269e6fa6492127dc29651b2dbec"
},
{
"name": "model.visual.blocks.0.mlp.linear_fc2.bias",
"sha256": "efd11a80c4fbeb83bb298e4f669d6c609a927fc6287a8b6a27e86b294bd28385"
},
{
"name": "model.visual.blocks.0.mlp.linear_fc2.weight",
"sha256": "3da5e8d459c94bc834d725cc214926218bbc1d41796e446427520f4131013742"
},
{
"name": "model.visual.blocks.0.norm1.bias",
"sha256": "705937610dbca85b31a2cbf27acd8c2fe5313c64136e4a67ee97fbe82834afa4"
},
{
"name": "model.visual.blocks.0.norm1.weight",
"sha256": "9060a81644cffaec43eccc4742dd0d1e951d187c78dc5cc8be6c77978bfc9b76"
},
{
"name": "model.visual.blocks.0.norm2.bias",
"sha256": "f8cb05c6c2522f543e8e0a4936ca6723867464d0f6dc2f16d2e64db231e5c849"
},
{
"name": "model.visual.blocks.0.norm2.weight",
"sha256": "9243906a61faf0d1067754ea6f2050bb9238ca3dc9eb95a66046a9b2daa1b727"
},
{
"name": "model.visual.blocks.1.attn.proj.bias",
"sha256": "31ec772a0876fe3f3c5916b9a4309ce319440f0f8f89f65333406fea3d212755"
},
{
"name": "model.visual.blocks.1.attn.proj.weight",
"sha256": "6e83b41938283f9e2e0f407d0a40a5203692ad180b22b6fede440e1c03079504"
},
{
"name": "model.visual.blocks.1.attn.qkv.bias",
"sha256": "83c5f50d34c576dc2e48c1220ded36f4366b2071132d3d2ec87321832927385a"
},
{
"name": "model.visual.blocks.1.attn.qkv.weight",
"sha256": "2a6ffd8e261ee288f7e697cef7472cbe8757a67f4108b1459ff20ba4d46d8765"
},
{
"name": "model.visual.blocks.1.mlp.linear_fc1.bias",
"sha256": "71b9a3dc487a99a47f06349196277fadc4561ed683c25afadfc60a96c17d38a2"
},
{
"name": "model.visual.blocks.1.mlp.linear_fc1.weight",
"sha256": "b803e9676fa45ac0ef102c5600ab370e17414a0223d8d5f99ac59c7ee6515781"
},
{
"name": "model.visual.blocks.1.mlp.linear_fc2.bias",
"sha256": "1dfd74a47f0cac956394c91419d31b0d9023c5d2ba48ed08c6474397b27a569b"
},
{
"name": "model.visual.blocks.1.mlp.linear_fc2.weight",
"sha256": "370c424e9045b5bf0686ce865bf77dedf36709977854123d5391331a7656be84"
},
{
"name": "model.visual.blocks.1.norm1.bias",
"sha256": "855c11e4acc32c28f5d2de55752470f8b3f6bfc0b6ecc3072981592fada24115"
},
{
"name": "model.visual.blocks.1.norm1.weight",
"sha256": "41b623b3b4f0de8da5224e72c047ab3d73b3c5cc94225a4cc1135d57471647d8"
},
{
"name": "model.visual.blocks.1.norm2.bias",
"sha256": "ffca97f45bdf96d1514440c3eaeafe90032cc2c6aca7fa4fecf6b90404ee2643"
},
{
"name": "model.visual.blocks.1.norm2.weight",
"sha256": "515aa82d70a1c3de12bad8ab3be9f4a73a9ad6d2bc3cf8a30110554c185e9920"
},
{
"name": "model.visual.blocks.10.attn.proj.bias",
"sha256": "084691af464265c01c9899b8c50f9a8b4331448c3ada1c54b703658358d37430"
},
{
"name": "model.visual.blocks.10.attn.proj.weight",
"sha256": "83043904bd54007a28103c095adb819d07eaccc80fc076056c8c6a5e74f71bb2"
},
{
"name": "model.visual.blocks.10.attn.qkv.bias",
"sha256": "88b106f693e8b47165cb0f4130dfc28d205efee69e45b3d9fa0e7feabe1bca61"
},
{
"name": "model.visual.blocks.10.attn.qkv.weight",
"sha256": "66018868326476c9c438a00305e5db4def3a7f363f640d77ae8e71dd9e1562fc"
},
{
"name": "model.visual.blocks.10.mlp.linear_fc1.bias",
"sha256": "fcb1d2664e4c4b4863091b95bfce08f7a2d9b9fbf81029f5d6adb8b037b275a9"
},
{
"name": "model.visual.blocks.10.mlp.linear_fc1.weight",
"sha256": "9bb65099244d1eeeea12cf49d5e9dd1bbfab4b039a34cccf9db2eb7f45af5311"
},
{
"name": "model.visual.blocks.10.mlp.linear_fc2.bias",
"sha256": "7a160acea3223f13c57257f6f0066e4bca1e6c40f79ea4006dbee5432e144d61"
},
{
"name": "model.visual.blocks.10.mlp.linear_fc2.weight",
"sha256": "8f8c219c8f938c4193d1e5e3b5d6f8cf7b9cb67d5a5adbbc5c87245966a7b53c"
},
{
"name": "model.visual.blocks.10.norm1.bias",
"sha256": "8d6c386a6ee79277437d7fc539f5cab10d8122411f80b240eb1de9f08cf43c5e"
},
{
"name": "model.visual.blocks.10.norm1.weight",
"sha256": "552e69b5ccfe7a476464598830f2077097636d922ca683f3cc1bc7523efd630b"
},
{
"name": "model.visual.blocks.10.norm2.bias",
"sha256": "fcdc2ce2a24bff41cb9317a31ac94470866e891e8acd910fa33164d9570e62a0"
},
{
"name": "model.visual.blocks.10.norm2.weight",
"sha256": "86251d3d0ad1f8a8557b9dc13685d2cbffc43fba39fb0061bce66084e7e0ff5c"
},
{
"name": "model.visual.blocks.11.attn.proj.bias",
"sha256": "a2fdc0aa6411f4a2a9a202eb9b3945ef029f3d7c9751b494ef8b2b54d5d84219"
},
{
"name": "model.visual.blocks.11.attn.proj.weight",
"sha256": "25459901c4dfb2616724f39d49db077a4b804eb83ceab2b446f271678f3b68fd"
},
{
"name": "model.visual.blocks.11.attn.qkv.bias",
"sha256": "a1a4acd9436a2770d86ea17ea92d4507ffaceb7e62e318bc3918a7ffd22dcfc4"
},
{
"name": "model.visual.blocks.11.attn.qkv.weight",
"sha256": "dec194ef8294e8faef372220745481eccec3e1079f3bff91c292b6ad9228da9c"
},
{
"name": "model.visual.blocks.11.mlp.linear_fc1.bias",
"sha256": "b49e8453d02c541b71053bf92ca48045c5c4af2ca4ee2263b01c58807e23b073"
},
{
"name": "model.visual.blocks.11.mlp.linear_fc1.weight",
"sha256": "3dd6247cbfe2788fc92cc8d4d38b0675ff179780f2ceb3a28a3d84c9be6b4ef8"
},
{
"name": "model.visual.blocks.11.mlp.linear_fc2.bias",
"sha256": "5a69b725264095b8a0c2da3f205414141738cef56c4eb50e5a1fefcb533e6416"
},
{
"name": "model.visual.blocks.11.mlp.linear_fc2.weight",
"sha256": "1ca4390c334009c37058c93ec52a7e6ec2422d7df16a6d37cc6e6090fe93d148"
},
{
"name": "model.visual.blocks.11.norm1.bias",
"sha256": "1f8b70a2688b672a8aacc56b6b3f64b44795b8f4245026ff20e31fd27168288d"
},
{
"name": "model.visual.blocks.11.norm1.weight",
"sha256": "71a0cc69c82fa2cb7ce6e4d140c4af9e0a8c620f87f05560eba77cd889a769e5"
},
{
"name": "model.visual.blocks.11.norm2.bias",
"sha256": "2847b9cc79dff7938deac2958d3f810866f0e3c7e6c0b127e9c2981d8a09ff47"
},
{
"name": "model.visual.blocks.11.norm2.weight",
"sha256": "956f8ca1e685ca5c410be2f26d82871f665aca9ebe6954f79529498b4c1b5a28"
},
{
"name": "model.visual.blocks.12.attn.proj.bias",
"sha256": "9f605c6d488cb22243901056e45e086b6645f86b4a034a29d075f49aad445c8f"
},
{
"name": "model.visual.blocks.12.attn.proj.weight",
"sha256": "a05952cf49ac576fff25c707046bc7b3e945bb8b422c4584cf654d4c34380949"
},
{
"name": "model.visual.blocks.12.attn.qkv.bias",
"sha256": "a1513b0c6599563a42402f34f651eac7602d2de9926b9c78f2df3cd2f7bb1d1e"
},
{
"name": "model.visual.blocks.12.attn.qkv.weight",
"sha256": "62410e6d19beeda096a76c12b3b8d93daec18b635b8dd73d0a461c0e8a68dbfa"
},
{
"name": "model.visual.blocks.12.mlp.linear_fc1.bias",
"sha256": "db53ec96dc75c247707913ffe390019c646bdf0becc999425ebdcb5585b03ab9"
},
{
"name": "model.visual.blocks.12.mlp.linear_fc1.weight",
"sha256": "3c5f44c301ca28addd15acc07c5e2162a0932bfdf919d941c4fb021f73db15a9"
},
{
"name": "model.visual.blocks.12.mlp.linear_fc2.bias",
"sha256": "e6366a38edf6676c312aa5624595976426efd08b2c2a4debdd4e3cb8958942fe"
},
{
"name": "model.visual.blocks.12.mlp.linear_fc2.weight",
"sha256": "2c789e61087576a99bdb335ebab439c89b935a3d6385e14ab3dcb89bbbba6edb"
},
{
"name": "model.visual.blocks.12.norm1.bias",
"sha256": "bfaed5882b1021013f832c396b9e20cc09c1cc21226bc19cbe5c7b51ee946e7c"
},
{
"name": "model.visual.blocks.12.norm1.weight",
"sha256": "5548136a38b0ccf40ffa67ef0bdb0c2869e7519c3a621c2d2e0f9d1e8359af93"
},
{
"name": "model.visual.blocks.12.norm2.bias",
"sha256": "a2f30f8615c7a722913249d15cd69c93f0671b73fa30df73c7b3a52c606d04fc"
},
{
"name": "model.visual.blocks.12.norm2.weight",
"sha256": "e1dda1d037239c414a7c9dcb3d817a9bfee8806bb816a60a8291084ed0f4b64b"
},
{
"name": "model.visual.blocks.13.attn.proj.bias",
"sha256": "30279899af0c00aa299209e2c7b93088e0ae38e7adcd7d138cb23cf29bb88b11"
},
{
"name": "model.visual.blocks.13.attn.proj.weight",
"sha256": "7754bb5bef5b10d173be0f843236f9fbe9708cb99f367171498da1c2dc82c885"
},
{
"name": "model.visual.blocks.13.attn.qkv.bias",
"sha256": "37f4e652687648493b512c35cbe4d23a6b7c7bcb5748b80f90f97e929e4f5666"
},
{
"name": "model.visual.blocks.13.attn.qkv.weight",
"sha256": "3ba8911a29443071be8ea0801e5eca7ea3e295344afd5a096ba7eb26cf7a8060"
},
{
"name": "model.visual.blocks.13.mlp.linear_fc1.bias",
"sha256": "4b2fcff903f47ba9b7632d044194f576630ff3cdbb7832d4db170081ceffa8bf"
},
{
"name": "model.visual.blocks.13.mlp.linear_fc1.weight",
"sha256": "93d65970bb64d1d8d32c9d0d1b46f3358f46761b71653301fc7b00119c885c73"
},
{
"name": "model.visual.blocks.13.mlp.linear_fc2.bias",
"sha256": "d5080ece39d523be6f79e8afe59aeda35614c6ac26410cbb9460f12da4272a9d"
},
{
"name": "model.visual.blocks.13.mlp.linear_fc2.weight",
"sha256": "a207567a3108d66963d58737fda881eeb854394ae7861add98772d88293a8bf8"
},
{
"name": "model.visual.blocks.13.norm1.bias",
"sha256": "99c76b92a1ca0c400f7854c2006a889fd14f9dddbf7919bd898a6b96ab3d186a"
},
{
"name": "model.visual.blocks.13.norm1.weight",
"sha256": "aac916cbc15af9c2d46cbc525f852980ff7c7a761dce99f7b1a0bd499caedd98"
},
{
"name": "model.visual.blocks.13.norm2.bias",
"sha256": "baada483be7ee40f2cab679f56521c6c491ebc15a010416feed41fb4f316a773"
},
{
"name": "model.visual.blocks.13.norm2.weight",
"sha256": "08873e19ad1618a7989cd8c148af4a087cfb99c8fdee123454ae515df715e262"
},
{
"name": "model.visual.blocks.14.attn.proj.bias",
"sha256": "d881564cb9d92f2d15fee1f39ce405f6518800e4b3cb7fcc5fc25a1909997e48"
},
{
"name": "model.visual.blocks.14.attn.proj.weight",
"sha256": "165137d81be341ea8d722f6857f1f85a4ad5d04f37070fb34f08e9d579b35341"
},
{
"name": "model.visual.blocks.14.attn.qkv.bias",
"sha256": "125b0dbbc7c0e5bbdc21cc1a3d1eba025e7926f5625a232882b1c8c7918e7deb"
},
{
"name": "model.visual.blocks.14.attn.qkv.weight",
"sha256": "7f60defa3a15c3d969d776a57bd7ea4e52d2a796b1b3be3c9d614600907bb307"
},
{
"name": "model.visual.blocks.14.mlp.linear_fc1.bias",
"sha256": "33267c4c1dbb9caa0b02d6e2a4972856eb127537573fc36bb9d8c99a2f3294af"
},
{
"name": "model.visual.blocks.14.mlp.linear_fc1.weight",
"sha256": "8c6511a311516c0388c4e378751650419e87910ba777e48a85a716bd987adfc6"
},
{
"name": "model.visual.blocks.14.mlp.linear_fc2.bias",
"sha256": "5d1e03bfba24ac7e0daddefff0f404e6ffc5d1b54611bd39d56a591534b2b113"
},
{
"name": "model.visual.blocks.14.mlp.linear_fc2.weight",
"sha256": "88071437b4de44140ce9e4fe6377875a8cc3561f44f89b8faed584d6fb302e98"
},
{
"name": "model.visual.blocks.14.norm1.bias",
"sha256": "c6e4caae445f71630828abadac07e1570337bbb3842e95addb470937de252eef"
},
{
"name": "model.visual.blocks.14.norm1.weight",
"sha256": "b77934071892ac0c1ce87e495ccf0ef5e66b0c964667d97bc8f75fc099b14af8"
},
{
"name": "model.visual.blocks.14.norm2.bias",
"sha256": "e18a3aff7a4b3c770fd8cc005e0c1998891d39a965ee4fd1669ca5cb7ca16249"
},
{
"name": "model.visual.blocks.14.norm2.weight",
"sha256": "17275c33b185468a90a1d210bb7e76b78e7b2a079cfef0c383731cc54a50f1e4"
},
{
"name": "model.visual.blocks.15.attn.proj.bias",
"sha256": "b9d2834ec1ad5b0762c132cfd209ec0c522d7b0fe4f19f33a8945c63de1c297a"
},
{
"name": "model.visual.blocks.15.attn.proj.weight",
"sha256": "c30d9549eeac07f55dbe832953dea45ff745d86c9dcbe1d65dfc8ccda6c0d621"
},
{
"name": "model.visual.blocks.15.attn.qkv.bias",
"sha256": "70ead455b42b0187aa11b55aba01a9356ace5426416f510115f7a3480d25ea4b"
},
{
"name": "model.visual.blocks.15.attn.qkv.weight",
"sha256": "8d75230b01d8a26b30304cc7396cd4b63fdb992cbe258859d6cdbc1c6e59a391"
},
{
"name": "model.visual.blocks.15.mlp.linear_fc1.bias",
"sha256": "cc35ed1ae07f0bdfaf055a7c06bfaa1227176ba98e63dd5ecff8c78024765338"
},
{
"name": "model.visual.blocks.15.mlp.linear_fc1.weight",
"sha256": "5d549e1efeb7b810dfdfd6336fba80d998d08ec7191155c62b57b4630c1475a1"
},
{
"name": "model.visual.blocks.15.mlp.linear_fc2.bias",
"sha256": "bceb9f2e26761c9557c8b8febe7c66caf24344b4e176e1be1249a23210da2a0a"
},
{
"name": "model.visual.blocks.15.mlp.linear_fc2.weight",
"sha256": "582bb9f57f9295b3047d5c4c3fcff3cadef3928d114f553a94e52a880536a561"
},
{
"name": "model.visual.blocks.15.norm1.bias",
"sha256": "543cf4d6b757de856858c06cb252c0329275b39fd063da0f0a39ea7133409abd"
},
{
"name": "model.visual.blocks.15.norm1.weight",
"sha256": "290ffeb2aa840a7b997ce6bf671b3117441f93bcc357ba55408fb8094f2f8ae9"
},
{
"name": "model.visual.blocks.15.norm2.bias",
"sha256": "f8b5bbc9783c7883016104137a04fdb8d2582000afc0ae8a4793b31bb85cea9a"
},
{
"name": "model.visual.blocks.15.norm2.weight",
"sha256": "99949640b1fc7683727c85eb90e943cd8d1e49d987964a36188245fd301c492c"
},
{
"name": "model.visual.blocks.16.attn.proj.bias",
"sha256": "45aa92a36c7790ffe7dc1abef2ef03d31cdae79d90e5c85bb81f17f9ded31f61"
},
{
"name": "model.visual.blocks.16.attn.proj.weight",
"sha256": "98b533ddfee762b7d74d10fb96baf31aa7747b423148b6c019d88ca340cec2a3"
},
{
"name": "model.visual.blocks.16.attn.qkv.bias",
"sha256": "237e5cfdbdafaec1a508856a36f6aa29cf10fbd4fc203e2b62fe0cbd2a4f808a"
},
{
"name": "model.visual.blocks.16.attn.qkv.weight",
"sha256": "2f1db061d5c7a08375e060ded963337f8f631fa5bbf1e95cb308fa2961047a1f"
},
{
"name": "model.visual.blocks.16.mlp.linear_fc1.bias",
"sha256": "e306f8880e77c9601a07fa574e19560e40535425654a2ce6dbd2264a1311226a"
},
{
"name": "model.visual.blocks.16.mlp.linear_fc1.weight",
"sha256": "8db17c757c2a8555017050ca430182a7cdc777b203d5902d4b9cd920fcca5c9a"
},
{
"name": "model.visual.blocks.16.mlp.linear_fc2.bias",
"sha256": "561d176c289589b49ea9564a85a3bf68b8aad6a412d9cc8f6c24cfb360c4fe19"
},
{
"name": "model.visual.blocks.16.mlp.linear_fc2.weight",
"sha256": "49ad171003405097c5434fbd36d10b33a5bd4626296df51a3792b87dbd53d59c"
},
{
"name": "model.visual.blocks.16.norm1.bias",
"sha256": "5a817b38dbe6f4b37cd3efadb3d69118d55519ea899fb81007955997871f0bc0"
},
{
"name": "model.visual.blocks.16.norm1.weight",
"sha256": "b2a5594385a871af78c187047a5931dac1045d814702e27c398ea71860581ca6"
},
{
"name": "model.visual.blocks.16.norm2.bias",
"sha256": "02c85da3552d645377a1b1c6aaa74c0c1a88ee6f516c20568b352e6633b46141"
},
{
"name": "model.visual.blocks.16.norm2.weight",
"sha256": "28191101af387835a4eabb4d6fe5ca4d9d54d8353fb1c2641d09d0da9101aa82"
},
{
"name": "model.visual.blocks.17.attn.proj.bias",
"sha256": "b995fe6134129cbde52f45c9da86615c60106c03da649993e43cf67613d60d26"
},
{
"name": "model.visual.blocks.17.attn.proj.weight",
"sha256": "be46bf57fe31977da712375bd34684a480ca9d9467225a769bc80d5942f71f71"
},
{
"name": "model.visual.blocks.17.attn.qkv.bias",
"sha256": "d4c7d08b3adc72b240cedc080c70c2a61b2e703fddee6c073af7feee5f70c49c"
},
{
"name": "model.visual.blocks.17.attn.qkv.weight",
"sha256": "71a8c29a51aa5e45bff3b1166575444e91db3da6ec79d6bf7d69bbdd6d51f331"
},
{
"name": "model.visual.blocks.17.mlp.linear_fc1.bias",
"sha256": "c2c7ce80bb5a534ba3ad678eb7d13b461ff3da8fd0012308c58e9c6db1994af2"
},
{
"name": "model.visual.blocks.17.mlp.linear_fc1.weight",
"sha256": "49c155bf7804f5b893be2e0eb44e3f8239b42e32c0e0996689feb76481916db2"
},
{
"name": "model.visual.blocks.17.mlp.linear_fc2.bias",
"sha256": "3543dc9ea9dcc8d9e9baaaf1d7eac39ac8d8aafcb35f7ddc701f008da2841dcf"
},
{
"name": "model.visual.blocks.17.mlp.linear_fc2.weight",
"sha256": "d966e5dbab0b087ff233d4f9a5fec07f371660e9ab762fda299d73662cdab631"
},
{
"name": "model.visual.blocks.17.norm1.bias",
"sha256": "440f74f03a0d5b42859a8502af2c8200c8145736a75ced25b93eb364d36a7ab3"
},
{
"name": "model.visual.blocks.17.norm1.weight",
"sha256": "20fbe0252222079b288c2bab30ab7edc8ff57804cd2cb45b55ec174dbf9cea97"
},
{
"name": "model.visual.blocks.17.norm2.bias",
"sha256": "fa498a15cd77c99a734df4b4b904a3cb64e2ccf788bd81d94a4d61e3ddfa625c"
},
{
"name": "model.visual.blocks.17.norm2.weight",
"sha256": "a372fb3a570b9663c98698e9c34849f9a254a8bcc2ca66d40b65fc1abdac9223"
},
{
"name": "model.visual.blocks.18.attn.proj.bias",
"sha256": "afba49361bff2244ec92490b160824a1daf4dec8da0c8242573ece13f3acb550"
},
{
"name": "model.visual.blocks.18.attn.proj.weight",
"sha256": "195c791f29ee6472f648b041a22a3df25b40d73c21cf7a3928a8b7096cacac51"
},
{
"name": "model.visual.blocks.18.attn.qkv.bias",
"sha256": "f24ff44a4d068d613fcf0d65b3ae591db7fffa4d24e5402be50a505a4fc6835a"
},
{
"name": "model.visual.blocks.18.attn.qkv.weight",
"sha256": "42b51f5436744f8b4d24522587a084f406a1a6729a4f65bb3c918d394ee5f9bd"
},
{
"name": "model.visual.blocks.18.mlp.linear_fc1.bias",
"sha256": "c05e7d052fa71779252a84fa9b216b2dde1d905e4a55a965019507b4388aec40"
},
{
"name": "model.visual.blocks.18.mlp.linear_fc1.weight",
"sha256": "620e115c144868e660d392987e99cd5b14ab26f25e45a1e6d588915f756fa94b"
},
{
"name": "model.visual.blocks.18.mlp.linear_fc2.bias",
"sha256": "e02136ac02a4a79865c2f26e56bfe065aa637a483cd88772d1f72dce3bb45d6e"
},
{
"name": "model.visual.blocks.18.mlp.linear_fc2.weight",
"sha256": "2b7a7b72c0dd691219747984a861fff41fd474bb650058375800ffe6aa6fffc5"
},
{
"name": "model.visual.blocks.18.norm1.bias",
"sha256": "5d38460248975be51074f603f2211cf5ba65b14430f684de366bf22704ca7102"
},
{
"name": "model.visual.blocks.18.norm1.weight",
"sha256": "e590e6f8daea8bdf03ff674d9766e7e243179c8a81825b70d9eafa1dcdd6fde3"
},
{
"name": "model.visual.blocks.18.norm2.bias",
"sha256": "a882134c6ed8fe75333ecd2d82c34c8c584ab69fb9f6c8da9d54353e6d130d00"
},
{
"name": "model.visual.blocks.18.norm2.weight",
"sha256": "c6f9a3a41d478c07227ab9a6897fe7f591d07473c97c964fa4296b1916a1c273"
},
{
"name": "model.visual.blocks.19.attn.proj.bias",
"sha256": "7aae3cbd67ecdfc987a9e2bc2d565cd21a959fa56f3fad637e4b1192c77d3946"
},
{
"name": "model.visual.blocks.19.attn.proj.weight",
"sha256": "017a5d2eef281d510311c87d41269ec1a6423616c041dea984c68bc5950b145d"
},
{
"name": "model.visual.blocks.19.attn.qkv.bias",
"sha256": "82e6c8931e7835eef091125e1e329eb9dd70d20cb2356327a4f44354e5c9d502"
},
{
"name": "model.visual.blocks.19.attn.qkv.weight",
"sha256": "1bd114fe81ddd2783d8e22f3f59cbba91ae59c1a730b5d5026c13a980bb1a651"
},
{
"name": "model.visual.blocks.19.mlp.linear_fc1.bias",
"sha256": "c7fd8a8e0a95ff901311863ed305534224ec817c2d563e4967259278f810f735"
},
{
"name": "model.visual.blocks.19.mlp.linear_fc1.weight",
"sha256": "4e8d6998cf4a10e046e3dcfc14ad4671876cd432d389812b557642fe3ffe57a7"
},
{
"name": "model.visual.blocks.19.mlp.linear_fc2.bias",
"sha256": "83feaf6b5e2211d5fd047cc946a9be5c57db31a591ea91d2cd3207e16318ac82"
},
{
"name": "model.visual.blocks.19.mlp.linear_fc2.weight",
"sha256": "302fab8a69584230543db939fce2056ca8b4c9e50b7c65f601265ca8efbb9505"
},
{
"name": "model.visual.blocks.19.norm1.bias",
"sha256": "5eeca33db80b90b93d0777d6ddaaf73cbd95e2dd3a5b52ef746840178059482f"
},
{
"name": "model.visual.blocks.19.norm1.weight",
"sha256": "99b992ba1fa6374554f5e8fcf63857a49cda0bb73c33f326d86a52a4eec3e887"
},
{
"name": "model.visual.blocks.19.norm2.bias",
"sha256": "b8ba8c5d60eb231852261fa9bac9189e1e1a16084cf2fe82dd548a104c47c9b8"
},
{
"name": "model.visual.blocks.19.norm2.weight",
"sha256": "13e34a5190bd1a9e1803d6f2e3f57382616104a95b0db42b0a0fefdc478b2578"
},
{
"name": "model.visual.blocks.2.attn.proj.bias",
"sha256": "94d31e40298d42be412971ba26ddd113e8682e247371436f2e5bacdb14b9a071"
},
{
"name": "model.visual.blocks.2.attn.proj.weight",
"sha256": "dd479ee7594d8caa111007a037291d91234266b9d8f09de2add0aeb0953b9493"
},
{
"name": "model.visual.blocks.2.attn.qkv.bias",
"sha256": "e478f23b292593a1b93ce482c5b4b800dc7c865a9351ceedbf71e7dbe2c839ae"
},
{
"name": "model.visual.blocks.2.attn.qkv.weight",
"sha256": "b9577c03c5e073f4e379afa9f2d657781bfdd23b8be9041543f5e9d4f7c6f370"
},
{
"name": "model.visual.blocks.2.mlp.linear_fc1.bias",
"sha256": "92822927532970df3391459e80177a0b72855fc8e184f1aced28d42474dc26c9"
},
{
"name": "model.visual.blocks.2.mlp.linear_fc1.weight",
"sha256": "f4207af90d4f85bec891129896d1bcf35d8c81bb7d82af38a11f70a80b42c41a"
},
{
"name": "model.visual.blocks.2.mlp.linear_fc2.bias",
"sha256": "96846bf63d90d63b9223305cb3021b969f16647e1cc512d0453cf4da8237a78c"
},
{
"name": "model.visual.blocks.2.mlp.linear_fc2.weight",
"sha256": "118bd485c957fbd7fe0224b57bb1dc7a67d139340d1a950171ed30aa5be5c2dc"
},
{
"name": "model.visual.blocks.2.norm1.bias",
"sha256": "ff3e5627aebc672534957ccbd3564d5e65ef5e74645a54285e164363ca0214d3"
},
{
"name": "model.visual.blocks.2.norm1.weight",
"sha256": "b09831809ae518327b59b3d2ea8b67ade90325ec1e963bd45efefa386ae861f0"
},
{
"name": "model.visual.blocks.2.norm2.bias",
"sha256": "041ab7a74d30b21b80cf991d6fd50866f196f661eeb5881d994ddedce03a1b00"
},
{
"name": "model.visual.blocks.2.norm2.weight",
"sha256": "b937844a775232ff4af0c32b666b212f4d5e4cb5ef9685944be89b2018485196"
},
{
"name": "model.visual.blocks.20.attn.proj.bias",
"sha256": "3724be6be85d8a586a60a7227349748b05743933463a1576776d4347687e691b"
},
{
"name": "model.visual.blocks.20.attn.proj.weight",
"sha256": "ece2f61c6e972dee3e094ea034ffe8fb6e0623e853fd3c1331388b1cf50054d0"
},
{
"name": "model.visual.blocks.20.attn.qkv.bias",
"sha256": "f61965f61e7cd0cb80daab22e6b59ac1994b124f18761d2239d47c9f8952ea13"
},
{
"name": "model.visual.blocks.20.attn.qkv.weight",
"sha256": "b05efd0c6804c165ef8c70e1a7b552b5de13f32a83d6346c5000d05eeae9500d"
},
{
"name": "model.visual.blocks.20.mlp.linear_fc1.bias",
"sha256": "80c68bdcaa54655543fd4fd15c4f0a192b07ef96c3520ad154363379e3f69469"
},
{
"name": "model.visual.blocks.20.mlp.linear_fc1.weight",
"sha256": "0d415b78dd18fb0651fcb021d01f008b656cf19d46851c8157e58fa4244b780f"
},
{
"name": "model.visual.blocks.20.mlp.linear_fc2.bias",
"sha256": "c0738d6639ab7238d26c194f4b83f4ce4174e38e333e8b3d3eb4cc0696276cec"
},
{
"name": "model.visual.blocks.20.mlp.linear_fc2.weight",
"sha256": "ba9b06eaf3fffee47ba0f016086b417e23a30dbea1f1384b532b0c5a0d2f0b95"
},
{
"name": "model.visual.blocks.20.norm1.bias",
"sha256": "648313103efec257b95894ee625bd548243209357def5915f78dca4afd48c224"
},
{
"name": "model.visual.blocks.20.norm1.weight",
"sha256": "bcc70baff3307b29328ed5a4867f382f3de9b67bac0d92848265f87a377af2df"
},
{
"name": "model.visual.blocks.20.norm2.bias",
"sha256": "9c0068afc1441c08b76b8d7d462ee672519933acc2d47cacda3ef62867dd4be4"
},
{
"name": "model.visual.blocks.20.norm2.weight",
"sha256": "3c9f2b6f304294ca66ac2b70cf85be07f203b448d5a8eacf1f04de352810ecc5"
},
{
"name": "model.visual.blocks.21.attn.proj.bias",
"sha256": "fb8467702fa017074afd5be36eedead2b1fcbb6a1d28183e12dae7a6fdd4ea79"
},
{
"name": "model.visual.blocks.21.attn.proj.weight",
"sha256": "5a836a34372e6477ab0d8bde75d331f35449a2bdd1e7bd3c2ac435be9eb5190e"
},
{
"name": "model.visual.blocks.21.attn.qkv.bias",
"sha256": "7025ee075c7a20ad3f6a90c91af062dd838fb9ef575eef79c8b997b198a21bdf"
},
{
"name": "model.visual.blocks.21.attn.qkv.weight",
"sha256": "1bc73e4f53c636002ab31bfa2a867ff061d94e53f9d53e08ce1789c5faca8a91"
},
{
"name": "model.visual.blocks.21.mlp.linear_fc1.bias",
"sha256": "7d6e2728dd71956c4d0c329b9ee2ce8213e30ab4c84a2ccee3473cded907d0ff"
},
{
"name": "model.visual.blocks.21.mlp.linear_fc1.weight",
"sha256": "f11706b23f523b71705779a54b8460fde29daeeaec9f5c8958aaa93fc4add855"
},
{
"name": "model.visual.blocks.21.mlp.linear_fc2.bias",
"sha256": "2f2eac305f50277365fe0e190dfaf7dbd7138bb553e28569fb7ea1826b6dc0e3"
},
{
"name": "model.visual.blocks.21.mlp.linear_fc2.weight",
"sha256": "e51e4e3a4ff5893c7700bc78a43d4a9db458f8e41fe5fc6b150de793748010e5"
},
{
"name": "model.visual.blocks.21.norm1.bias",
"sha256": "336bdc6749a73a605b64ca4c4cd4a08af90482fafcb7cf05bdaa61e976f3e574"
},
{
"name": "model.visual.blocks.21.norm1.weight",
"sha256": "3caa6e2036303e5e11ab50c5ccee24c75645b942f3dce038c096bbaa75d6deca"
},
{
"name": "model.visual.blocks.21.norm2.bias",
"sha256": "8007af71a860e421bf704acae4232a153620e0566609becc37238748cd469f9f"
},
{
"name": "model.visual.blocks.21.norm2.weight",
"sha256": "3640518f41c00512409f358742fd1ef8017979c1f15f72f60cd45d586cba7e9c"
},
{
"name": "model.visual.blocks.22.attn.proj.bias",
"sha256": "79dbdb3729648645122510f46f2a2bf97d4db3f5bfb8049a9b0714edddf7e905"
},
{
"name": "model.visual.blocks.22.attn.proj.weight",
"sha256": "9861347cffa1dab0dbc904aa37a9e7f415c3b4de39568f2ec1875d27f69ba622"
},
{
"name": "model.visual.blocks.22.attn.qkv.bias",
"sha256": "4f6ffae200c2c25b7598ae8164e562d254ca2174271ee7377f62b492ccc7610f"
},
{
"name": "model.visual.blocks.22.attn.qkv.weight",
"sha256": "3597ec85b25e4499c7ad014af1a247feedcc58d497846b45f7386dff69c7ad68"
},
{
"name": "model.visual.blocks.22.mlp.linear_fc1.bias",
"sha256": "97b74441ce1659bce357e73b0809439b3d0cef4ff8a330d5616505fcfe3c4157"
},
{
"name": "model.visual.blocks.22.mlp.linear_fc1.weight",
"sha256": "f1e80b5d72f4b1bc5e8aa84c52997de280d19edfdd7b7f10e4bf5bbc084d14f4"
},
{
"name": "model.visual.blocks.22.mlp.linear_fc2.bias",
"sha256": "fe12fcd1d43835a261cfc88160fa22ee191fccda1019eaa138c9833d26b7d816"
},
{
"name": "model.visual.blocks.22.mlp.linear_fc2.weight",
"sha256": "9474fc98d0fbd9ca35ae72b83584646bd59a2165cb3f2c9ea5e73b1365dc4cc8"
},
{
"name": "model.visual.blocks.22.norm1.bias",
"sha256": "960cce487b14523a0d5e4898654cad4681390c5fd163826564c0a0f1cb1c3181"
},
{
"name": "model.visual.blocks.22.norm1.weight",
"sha256": "c324394cc64740f40fc3f0302a7eb9b5cc2e7a6ab51e23dde36e595a6aa159fe"
},
{
"name": "model.visual.blocks.22.norm2.bias",
"sha256": "25754395e802dc1b9bf1466e8a229a2f4580f9a4d26147f229b43ae03ca09cbf"
},
{
"name": "model.visual.blocks.22.norm2.weight",
"sha256": "bd8d65ef54781cfe795b11fb901866d54190b47ba6cba3a33565eeb845bae250"
},
{
"name": "model.visual.blocks.23.attn.proj.bias",
"sha256": "a9265e706f4eac0de66b34904a5a6074dca190ca89f7c639392d6266a0684858"
},
{
"name": "model.visual.blocks.23.attn.proj.weight",
"sha256": "fecf4ed60dbfedb7e00e705e0851c971e8ffbee0e3d1024732db7c8e31bc0e53"
},
{
"name": "model.visual.blocks.23.attn.qkv.bias",
"sha256": "9829e46aaef494ac7112f44d2f3c2489b64a1dbc7e118039dfd93e5635c565f5"
},
{
"name": "model.visual.blocks.23.attn.qkv.weight",
"sha256": "698ffc84a95574a3e9f73d1ea61df80c0e59f0f546167ceaa824d00ead3a290c"
},
{
"name": "model.visual.blocks.23.mlp.linear_fc1.bias",
"sha256": "a6e9699f9033d3dc42a57c9819d4bda2453b5d56935e0cad34ba2d20a8f94ae6"
},
{
"name": "model.visual.blocks.23.mlp.linear_fc1.weight",
"sha256": "5f688785d08f617ec7b9ede836dfde41e081cb9a7236bedb9468299dc52eca7c"
},
{
"name": "model.visual.blocks.23.mlp.linear_fc2.bias",
"sha256": "0b17666cc3012787d5027ba3121713ab76520acb90b86e966c43e71543226836"
},
{
"name": "model.visual.blocks.23.mlp.linear_fc2.weight",
"sha256": "cf3e204c5071aadd8717869214c77eb7857b5928d8006f6fca2c5967f5fc2dd6"
},
{
"name": "model.visual.blocks.23.norm1.bias",
"sha256": "2f2eb1e5c8696cdbf6400023a1cb6d9caa12da5804cbbf19d8654bf1907d7bdc"
},
{
"name": "model.visual.blocks.23.norm1.weight",
"sha256": "f860d728f031c6ea32600b70772c1c047ace2425416a6c665986db83c3234634"
},
{
"name": "model.visual.blocks.23.norm2.bias",
"sha256": "88b51d875b7d913ed0451c94c530bc23cc2728981c9afc74d5bfde0e3080cd26"
},
{
"name": "model.visual.blocks.23.norm2.weight",
"sha256": "a40aacb8e70ff0a7cca9f1159df2ef9ddd01326075f663a32c8e98b2b935e4dc"
},
{
"name": "model.visual.blocks.3.attn.proj.bias",
"sha256": "644a79ae4e2b1397bc80527f9c9b1dfdffea4fd1febb08bc203b93e224c414bf"
},
{
"name": "model.visual.blocks.3.attn.proj.weight",
"sha256": "0f2842ed03cd0864e4bc89cecd981a3a260d5ed595ef12e6502f3e82d7e34b7e"
},
{
"name": "model.visual.blocks.3.attn.qkv.bias",
"sha256": "1629911c657ca23c3b78a6dc3c60bfe0c449e02ba35d9f9a43b03153446cb943"
},
{
"name": "model.visual.blocks.3.attn.qkv.weight",
"sha256": "459ca15a0a59f3befe86208004443c85c8930e1739bbeb6efe128e1901985167"
},
{
"name": "model.visual.blocks.3.mlp.linear_fc1.bias",
"sha256": "aea71fe31e83a5f4c78b99a3a20ca2a124352ab46d6f2ac342982820c6a71718"
},
{
"name": "model.visual.blocks.3.mlp.linear_fc1.weight",
"sha256": "f377817ec651cec97f2394217dc1d59eea559f01a7341b3ee6b6c18ffd42fec4"
},
{
"name": "model.visual.blocks.3.mlp.linear_fc2.bias",
"sha256": "3c24d65817d8d13c130204391b299f6b1df7f20df005065a1fc0a697aa616aa3"
},
{
"name": "model.visual.blocks.3.mlp.linear_fc2.weight",
"sha256": "f32e55c1195536c89122fd4c3ba491e4ac91822ef30e14d0375b1b1abadae5d3"
},
{
"name": "model.visual.blocks.3.norm1.bias",
"sha256": "918d93e6fea721c4bb9d64799e489ff12ac848b09375e3a6b62f664b19028c69"
},
{
"name": "model.visual.blocks.3.norm1.weight",
"sha256": "2eb4b6d1a0dd291257ef0a81963a1ac0af903bf647f44b53dcccbbff3c173973"
},
{
"name": "model.visual.blocks.3.norm2.bias",
"sha256": "c128c8eb4853b6bbbadb6637b6b22a59c7e346a6a1a3c4f0dec4d6913bee5477"
},
{
"name": "model.visual.blocks.3.norm2.weight",
"sha256": "4a4812f5570c1ad14dc4cf0778e53f2d11ed6bf76da1c235aa3af65dce32d7fc"
},
{
"name": "model.visual.blocks.4.attn.proj.bias",
"sha256": "76c005afe47cd8d4807f0d966b2ff9078089e2bf7b8ca23d4126175b0f020bd1"
},
{
"name": "model.visual.blocks.4.attn.proj.weight",
"sha256": "86032b4c08f68dce1bcc21b0cc49e471af55ca1459853ec8b81fd61c32906905"
},
{
"name": "model.visual.blocks.4.attn.qkv.bias",
"sha256": "c6f9cb7e948db202a0bea1d6099ae301cabfc443ed18310a619fed281ebb32de"
},
{
"name": "model.visual.blocks.4.attn.qkv.weight",
"sha256": "0ce89e7add597a749e6b24e7043d6be6879b071b5b2c80c16a5c1e95e7991c4a"
},
{
"name": "model.visual.blocks.4.mlp.linear_fc1.bias",
"sha256": "667256b739c39a263caf48e8c7ec3bab50470579338625bf18d8986cf653551a"
},
{
"name": "model.visual.blocks.4.mlp.linear_fc1.weight",
"sha256": "f4d08b31eb75e018c79540b5bcd32007d801928a00cb0bec260b3c2e8b282e1a"
},
{
"name": "model.visual.blocks.4.mlp.linear_fc2.bias",
"sha256": "8e44330faff0f8fe3b3913cf21e8f0901dc2d6a95f5f298277071bff3ad3b379"
},
{
"name": "model.visual.blocks.4.mlp.linear_fc2.weight",
"sha256": "6a91eeb4ef9830bd2a46c3da6e5fefdd6254d32ce3eb6d5720bd02cdabff40fb"
},
{
"name": "model.visual.blocks.4.norm1.bias",
"sha256": "e1e8602624a6e8be30c8748108f0a2cfd49d9d816cb076e4d157bed59417fdaf"
},
{
"name": "model.visual.blocks.4.norm1.weight",
"sha256": "70ccaa8a6989a2e1fd49286360c690849c91532875e4575da8c85374eb017d98"
},
{
"name": "model.visual.blocks.4.norm2.bias",
"sha256": "53abdfec31e34b370683e42bddbc212c91a16dbcf55e964eeeefe4621dbbbef8"
},
{
"name": "model.visual.blocks.4.norm2.weight",
"sha256": "ae98d2a0577b15be683404ed7146d31a050e75c2c9db9e49ab59d09c67a5b323"
},
{
"name": "model.visual.blocks.5.attn.proj.bias",
"sha256": "a51ef99055dd9d4d7bff3b61ceb3e8d212d8f84ca3e65f0beff3ba0e677f00ef"
},
{
"name": "model.visual.blocks.5.attn.proj.weight",
"sha256": "b3b5ac1fcb02281c9d0530ab2b305e54625d98b9727c1e5b66063313d52381f3"
},
{
"name": "model.visual.blocks.5.attn.qkv.bias",
"sha256": "044d33c62b3fa0d60f1575e2d3346eb60d083bff238fdd9177dca29bcc228d00"
},
{
"name": "model.visual.blocks.5.attn.qkv.weight",
"sha256": "5addd0586a7cdd1d7011e1daf9e40a6e77f897a2ba116da432c195a4d7d70fef"
},
{
"name": "model.visual.blocks.5.mlp.linear_fc1.bias",
"sha256": "5d508693f56396b77ea8f775a9787098e64c521654a4f1458506e552795117f7"
},
{
"name": "model.visual.blocks.5.mlp.linear_fc1.weight",
"sha256": "487cb888c75c4c4c7dc90e6e680fb4767345ac429525507ea129a968b885664e"
},
{
"name": "model.visual.blocks.5.mlp.linear_fc2.bias",
"sha256": "9a6fda5026fece183c552dc200f93db58232e64aa959c5702f94ba5728730fad"
},
{
"name": "model.visual.blocks.5.mlp.linear_fc2.weight",
"sha256": "745aac9e7c9d3daac61f725d7f3356aa29ea31bacca2ecb88156a45621a0f9e3"
},
{
"name": "model.visual.blocks.5.norm1.bias",
"sha256": "743a978d261af96d020f6f20284349bb78f3425581ec1f8121efb5e9e7cea9ff"
},
{
"name": "model.visual.blocks.5.norm1.weight",
"sha256": "76f8bb0138578e885c4ab2662320538d34ae7cb95c2d703a401d2f9743b4f974"
},
{
"name": "model.visual.blocks.5.norm2.bias",
"sha256": "3ceee1808df66a9bbb512bfc7ea66fdef4f7f529ded91a2c7068ae16ee607ecf"
},
{
"name": "model.visual.blocks.5.norm2.weight",
"sha256": "93a302a8287b9e6998d5011ec3392187cebb854f34db3178da50b6b23a7eda73"
},
{
"name": "model.visual.blocks.6.attn.proj.bias",
"sha256": "479c7a941d5daee326f94cdba52fd0d9a7a237455a2e61cd517dcc563677abc3"
},
{
"name": "model.visual.blocks.6.attn.proj.weight",
"sha256": "8f13171d9b9017d9dc40c4b0b648400a8af9b1bc67708997f0bb9b0f5516f11e"
},
{
"name": "model.visual.blocks.6.attn.qkv.bias",
"sha256": "b92cfce90ddb8d36d5c8a3688652f2f235e6b02c8170680350e75d7f3cb57298"
},
{
"name": "model.visual.blocks.6.attn.qkv.weight",
"sha256": "c1254186e595966ad04c129f33e1b7b80da6f42c103882630411f271da61c89f"
},
{
"name": "model.visual.blocks.6.mlp.linear_fc1.bias",
"sha256": "2ba9d2c07fd65b863529adf902a9e26898adc261381edc1e56e37b19ae81c979"
},
{
"name": "model.visual.blocks.6.mlp.linear_fc1.weight",
"sha256": "013c8256f80f02d63e136d67abcc0f1550a8e56cfb41cd233144e5d0deabb309"
},
{
"name": "model.visual.blocks.6.mlp.linear_fc2.bias",
"sha256": "d0a6b92902450aa618d0a312e4354bae51fd3c0e14f93d63ccf0100162069c0f"
},
{
"name": "model.visual.blocks.6.mlp.linear_fc2.weight",
"sha256": "d5166b8915ef4558106dc5bc2c8daa840025bb1ed7e68a4af938f85efdf29b0e"
},
{
"name": "model.visual.blocks.6.norm1.bias",
"sha256": "c222f9d96835b453b54ae974153f896525e0db92b72f9c9abe78d53bc9c6782d"
},
{
"name": "model.visual.blocks.6.norm1.weight",
"sha256": "93608740ca46049ee4a4e5096706b1353beaa506771d1e7288a9f3fab78d7f30"
},
{
"name": "model.visual.blocks.6.norm2.bias",
"sha256": "2446518553380ab48d7b1318d0dc5f9e4703931172c5774a2e28bccc636d6715"
},
{
"name": "model.visual.blocks.6.norm2.weight",
"sha256": "c28f656f4edf8aad973538f153e671b365b7fcf218604b4dcfb65c3444cd1d6f"
},
{
"name": "model.visual.blocks.7.attn.proj.bias",
"sha256": "02687539a534829a814dc6bdcdf2c66a64f7d8b40be2975462306bd999073983"
},
{
"name": "model.visual.blocks.7.attn.proj.weight",
"sha256": "fb0a2c7a6ccf2ec7ac94bc248864fe966d3d4ddfaea54228ac86cb3a2fbda677"
},
{
"name": "model.visual.blocks.7.attn.qkv.bias",
"sha256": "51544cd4f29862405c85869cf6bede6772b8594f819468ec87dcfbe0722fc852"
},
{
"name": "model.visual.blocks.7.attn.qkv.weight",
"sha256": "e6db2acbd3fc7bad4e167a1fd0e266eb3898e61e6ed6d4173d761a074573019f"
},
{
"name": "model.visual.blocks.7.mlp.linear_fc1.bias",
"sha256": "70d61d131f9539413e65115c3c698cb118c495b6d44d653f5e840494344316cb"
},
{
"name": "model.visual.blocks.7.mlp.linear_fc1.weight",
"sha256": "90981203fc062643ef5e85afa99304f09b12d4db9296594122c9ed40fbe4fe2a"
},
{
"name": "model.visual.blocks.7.mlp.linear_fc2.bias",
"sha256": "b859a67e2f6f94bef67a6b27e23364ed94ab7d2a75584bfec17f6f3478d60a69"
},
{
"name": "model.visual.blocks.7.mlp.linear_fc2.weight",
"sha256": "cc7fd8a1c8718df5ece40b5fed2a932683db9fe67248591061f0e4d729c44920"
},
{
"name": "model.visual.blocks.7.norm1.bias",
"sha256": "2e81f5fafaa91341cde22f32fb6d0cb7fc3615e45291c1a27a57c7184001ded3"
},
{
"name": "model.visual.blocks.7.norm1.weight",
"sha256": "1bcc706e78dd9b26f4f68b73a9370544b7f8486657daa28d532106379c70ee31"
},
{
"name": "model.visual.blocks.7.norm2.bias",
"sha256": "c7f6848fa40bd1acffa80601a19d85fed02339c9340faaebeee216e5210a5d67"
},
{
"name": "model.visual.blocks.7.norm2.weight",
"sha256": "1df8bf267d7d5554ca473d3671ff08ee9c44c69a848f5fabef569cee62cae999"
},
{
"name": "model.visual.blocks.8.attn.proj.bias",
"sha256": "78bdff59b56e8675a5f71321d655be8de347c39d7626ec91adbe740d59d75a3b"
},
{
"name": "model.visual.blocks.8.attn.proj.weight",
"sha256": "f1f1a5ded3173b1e39d48c9315d50cdc51d0c46213ec88d2e05e6c4fc7f9eb00"
},
{
"name": "model.visual.blocks.8.attn.qkv.bias",
"sha256": "cdfaf51f64eec4b77aad4f4728500f4e65e44cda2c879a84f901492370956b90"
},
{
"name": "model.visual.blocks.8.attn.qkv.weight",
"sha256": "f8d3729497c12a1c6e9cb1e0781981e638cff081e629d56c040250b716fd1a3f"
},
{
"name": "model.visual.blocks.8.mlp.linear_fc1.bias",
"sha256": "21868a7ecfbe89e7145893f0859a82398bdd1eec9b3aa14679cfa0651c0daae5"
},
{
"name": "model.visual.blocks.8.mlp.linear_fc1.weight",
"sha256": "ef8727c4857835f124bade52f9e6704d2c83aca16b85a6bf981cae3174fbd98c"
},
{
"name": "model.visual.blocks.8.mlp.linear_fc2.bias",
"sha256": "4efdeaee423e07c2c25bd6467352b9a53ccf0623fa0ebd3eea4be9599df58044"
},
{
"name": "model.visual.blocks.8.mlp.linear_fc2.weight",
"sha256": "9a954be9548c69fdc1de64aef29c63bbe7e5c91567c33228edfba3565297399b"
},
{
"name": "model.visual.blocks.8.norm1.bias",
"sha256": "05e8c3a92fb3010011ed02f37e1db5c74a9016aa057d0750cf26e360a69871b7"
},
{
"name": "model.visual.blocks.8.norm1.weight",
"sha256": "1131f92661993a6e61cf7837ded345f54d86c1fe312975375aa6459d61bffdd9"
},
{
"name": "model.visual.blocks.8.norm2.bias",
"sha256": "a55ee8b24a2748367852e890414ef830485ecd19bef3a5ab11e9a0d6111af666"
},
{
"name": "model.visual.blocks.8.norm2.weight",
"sha256": "114385b9e9a0798dca8ff52554dc5765f15b1e7792173b14af78444749c41c7a"
},
{
"name": "model.visual.blocks.9.attn.proj.bias",
"sha256": "1aa757ea62c967739ddede7164acedf908f3f3e78d15610720b4a4a5226b31a9"
},
{
"name": "model.visual.blocks.9.attn.proj.weight",
"sha256": "931e0a4acf4cbf71c2e728ae481272d3399383a2406e6a1f15cfe232bfec4d12"
},
{
"name": "model.visual.blocks.9.attn.qkv.bias",
"sha256": "3946b505c1b7004c265c30ec3db930c8543609ca4e45e549007927f6e242c30a"
},
{
"name": "model.visual.blocks.9.attn.qkv.weight",
"sha256": "2199b59ec26168ed66dc893db2e021fc3328416dd0b5ff8fcddcb47263ac6233"
},
{
"name": "model.visual.blocks.9.mlp.linear_fc1.bias",
"sha256": "35e9367fe96affa535ab8b6000bc90efddd4143ff4ec76d00127e002a2150d8c"
},
{
"name": "model.visual.blocks.9.mlp.linear_fc1.weight",
"sha256": "5dfbb6be057e406214a007e3e00d8396e5cb8e4bc13a1b19cc1314f74eed79af"
},
{
"name": "model.visual.blocks.9.mlp.linear_fc2.bias",
"sha256": "3a4d67ae41597da68bbded109bb3d85475d5e1192e1498b8aa6cbaf69e8fb44a"
},
{
"name": "model.visual.blocks.9.mlp.linear_fc2.weight",
"sha256": "5e1671f472d661141448f4d4558241fe6eeff9b98d5db9f942dd1bc91c3625cc"
},
{
"name": "model.visual.blocks.9.norm1.bias",
"sha256": "3cc07aa4deaa4dedf95c343b9667b377ab4cdc8e39b3e38221e4b392b8b34fcb"
},
{
"name": "model.visual.blocks.9.norm1.weight",
"sha256": "ef0deee9e8f1ac46e3e7010aafa20baf3e5a010e1e4df6f27107df9093967192"
},
{
"name": "model.visual.blocks.9.norm2.bias",
"sha256": "91c3ddadd1de4dc6add763a9b9b957e637fc682f98ee3be0215bc0f547995aa7"
},
{
"name": "model.visual.blocks.9.norm2.weight",
"sha256": "9b3174cfacddaad5eee80198afdf3dc5017cd11cdabb282a4d3bd8d52506517b"
},
{
"name": "model.visual.deepstack_merger_list.0.linear_fc1.bias",
"sha256": "29d422aa0ea6a9a3878ece2be6674e18820b78b3f3e1194b313d477eb9d42243"
},
{
"name": "model.visual.deepstack_merger_list.0.linear_fc1.weight",
"sha256": "7ed65bc027972c4da84d6e5f6e5c0766ee509fd8cf0994554b8896078e127d7d"
},
{
"name": "model.visual.deepstack_merger_list.0.linear_fc2.bias",
"sha256": "b01ac6494f8a720311dc07a4e85906bae4452c7da8eb8d39056daff725453c39"
},
{
"name": "model.visual.deepstack_merger_list.0.linear_fc2.weight",
"sha256": "9849e0a84b9a83bf0908f169d89988971d235ac71e5421858d23d726c2863f9d"
},
{
"name": "model.visual.deepstack_merger_list.0.norm.bias",
"sha256": "a24d103831a4aa0ec9e75c94a05a3368afd20369ea0b0dc34a6693bd8499b63e"
},
{
"name": "model.visual.deepstack_merger_list.0.norm.weight",
"sha256": "7bbee01734b8aba74f91369d456823b2d7376359774193b872bcd2e19693b931"
},
{
"name": "model.visual.deepstack_merger_list.1.linear_fc1.bias",
"sha256": "82d1ed3c3b40662b8ae5319d9f44b0cff28323304def115d3cd15e5f8781075c"
},
{
"name": "model.visual.deepstack_merger_list.1.linear_fc1.weight",
"sha256": "e8150d17d6d639896ced950d59e5fc0278825bdf99365eb1e7f2c505296a2bc9"
},
{
"name": "model.visual.deepstack_merger_list.1.linear_fc2.bias",
"sha256": "ecccb71fad6b3ba7cb2c860fe244e238b7ad939804449b5978a3ac673549ed73"
},
{
"name": "model.visual.deepstack_merger_list.1.linear_fc2.weight",
"sha256": "5f09a55a4c5139e6fb34f1304f7b1514f4b1123ab539552ac953f674762e610a"
},
{
"name": "model.visual.deepstack_merger_list.1.norm.bias",
"sha256": "a8142b1bf541e9901027615bde924035d9ef7cc0fdcf2ac541d65ad3535697e2"
},
{
"name": "model.visual.deepstack_merger_list.1.norm.weight",
"sha256": "e8e70a4a272313b559f672aceaa18befddbdf63d22520eabdada8fb6e3d03d29"
},
{
"name": "model.visual.deepstack_merger_list.2.linear_fc1.bias",
"sha256": "7d96e9ee99e14a6624f6aa605d5bacc2028f54da3e8a3035c412913905748666"
},
{
"name": "model.visual.deepstack_merger_list.2.linear_fc1.weight",
"sha256": "f0ad7194d37c54aaa6e1d5d7939848ffe6c77053f06bc0d7341eed940d2f590c"
},
{
"name": "model.visual.deepstack_merger_list.2.linear_fc2.bias",
"sha256": "2a8eaea31432a5718607652e30a046819bd354f38412d28adf269d2a9558d394"
},
{
"name": "model.visual.deepstack_merger_list.2.linear_fc2.weight",
"sha256": "8b30275e0eadc872a86e8fdf3443ec7029cc77b48ba7623a1f914745060f4499"
},
{
"name": "model.visual.deepstack_merger_list.2.norm.bias",
"sha256": "dc3ec18dd0c64b05801a2f5590795fbd59ff5389cbdd62f320e37015807b74e9"
},
{
"name": "model.visual.deepstack_merger_list.2.norm.weight",
"sha256": "7e51e7ab2cc9d443caa8326e2d60f1b449d69c80812eb101a79ee1c81a04c2e0"
},
{
"name": "model.visual.merger.linear_fc1.bias",
"sha256": "01159dc931043923d7877c5ab2100c944840604eb0bc24e2b9550d5f87625cdc"
},
{
"name": "model.visual.merger.linear_fc1.weight",
"sha256": "a4eed69453cf9bf38a8f36532b235c0b41130788aa509a1861d2aeb67591b50d"
},
{
"name": "model.visual.merger.linear_fc2.bias",
"sha256": "b8632474f436b57239e6af4f8c1416e0c950ead2544408e6bc46109457c244b4"
},
{
"name": "model.visual.merger.linear_fc2.weight",
"sha256": "fc9fa6edb038c4e8a349c2ccfabaff29e27d1d483f46948522c909d4b856d92f"
},
{
"name": "model.visual.merger.norm.bias",
"sha256": "cfa84f209b21feb03e7554a2467f63acd18cb228a6eedaa13a5a3dad7fa9c5cc"
},
{
"name": "model.visual.merger.norm.weight",
"sha256": "f2b3105e470bc9c7ee61970603d674ac32fa5ef9e695e8dc868f479a50880703"
},
{
"name": "model.visual.patch_embed.proj.bias",
"sha256": "2b0479d4f1491215fd57ea7a18a1c0b6edb805070005c6156687e9af7d006059"
},
{
"name": "model.visual.patch_embed.proj.weight",
"sha256": "2ee82d059e4c965c024093b8818150b86785e9f56cb467ad2fb3e1f9b6286471"
},
{
"name": "model.visual.pos_embed.weight",
"sha256": "0deb9bcc4847f74f6a0598a744b4a81035e6d662ab1b564977a910ce61a06688"
}
],
"tensors": {
"model.language_model.embed_tokens.weight": {
"dtype": "BF16",
"shape": [
151686,
2560
],
"data_offsets": [
0,
776632320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776632320,
776637440
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776637440,
776642560
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776642560,
776662016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776662016,
776681472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776681472,
776686592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776686592,
776686848
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776686848,
776688896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776688896,
776694016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776694016,
776694272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776694272,
776702464
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776702464,
776704512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776704512,
776709632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776709632,
776714752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776714752,
776734208
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776734208,
776753664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776753664,
776758784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776758784,
776759040
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776759040,
776761088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776761088,
776766208
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776766208,
776766464
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776766464,
776774656
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776774656,
776776704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776776704,
776781824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776781824,
776786944
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776786944,
776806400
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776806400,
776825856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776825856,
776830976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776830976,
776831232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776831232,
776833280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776833280,
776838400
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776838400,
776838656
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776838656,
776846848
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776846848,
776848896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776848896,
776854016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776854016,
776859136
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776859136,
776878592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776878592,
776898048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776898048,
776903168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776903168,
776903424
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776903424,
776905472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776905472,
776910592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776910592,
776910848
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776910848,
776919040
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776919040,
776921088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776921088,
776926208
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776926208,
776931328
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776931328,
776950784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776950784,
776970240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776970240,
776975360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776975360,
776975616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776975616,
776977664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776977664,
776982784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776982784,
776983040
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776983040,
776991232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776991232,
776993280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776993280,
776998400
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776998400,
777003520
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777003520,
777022976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777022976,
777042432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777042432,
777047552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777047552,
777047808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777047808,
777049856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777049856,
777054976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777054976,
777055232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777055232,
777063424
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777063424,
777065472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777065472,
777070592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777070592,
777075712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777075712,
777095168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777095168,
777114624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777114624,
777119744
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777119744,
777120000
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777120000,
777122048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777122048,
777127168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777127168,
777127424
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777127424,
777135616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777135616,
777137664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777137664,
777142784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777142784,
777147904
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777147904,
777167360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777167360,
777186816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777186816,
777191936
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777191936,
777192192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777192192,
777194240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777194240,
777199360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777199360,
777199616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777199616,
777207808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777207808,
777209856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777209856,
777214976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777214976,
777220096
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777220096,
777239552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777239552,
777259008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777259008,
777264128
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777264128,
777264384
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777264384,
777266432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777266432,
777271552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777271552,
777271808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777271808,
777280000
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777280000,
777282048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777282048,
777287168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777287168,
777292288
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777292288,
777311744
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777311744,
777331200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777331200,
777336320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777336320,
777336576
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777336576,
777338624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777338624,
777343744
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777343744,
777344000
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777344000,
777352192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777352192,
777354240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777354240,
777359360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777359360,
777364480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777364480,
777383936
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777383936,
777403392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777403392,
777408512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777408512,
777408768
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777408768,
777410816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777410816,
777415936
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777415936,
777416192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777416192,
777424384
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777424384,
777426432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777426432,
777431552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777431552,
777436672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777436672,
777456128
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777456128,
777475584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777475584,
777480704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777480704,
777480960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777480960,
777483008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777483008,
777488128
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777488128,
777488384
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777488384,
777496576
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777496576,
777498624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777498624,
777503744
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777503744,
777508864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777508864,
777528320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777528320,
777547776
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777547776,
777552896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777552896,
777553152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777553152,
777555200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777555200,
777560320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777560320,
777560576
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777560576,
777568768
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777568768,
777570816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777570816,
777575936
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777575936,
777581056
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777581056,
777600512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777600512,
777619968
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777619968,
777625088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777625088,
777625344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777625344,
777627392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777627392,
777632512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777632512,
777632768
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777632768,
777640960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777640960,
777643008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777643008,
777648128
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777648128,
777653248
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777653248,
777672704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777672704,
777692160
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777692160,
777697280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777697280,
777697536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777697536,
777699584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777699584,
777704704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777704704,
777704960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777704960,
777713152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777713152,
777715200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777715200,
777720320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777720320,
777725440
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777725440,
777744896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777744896,
777764352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777764352,
777769472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777769472,
777769728
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777769728,
777771776
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777771776,
777776896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777776896,
777777152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777777152,
777785344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777785344,
777787392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777787392,
777792512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777792512,
777797632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777797632,
777817088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777817088,
777836544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777836544,
777841664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777841664,
777841920
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777841920,
777843968
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777843968,
777849088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777849088,
777849344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777849344,
777857536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777857536,
777859584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777859584,
777864704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777864704,
777869824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777869824,
777889280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777889280,
777908736
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777908736,
777913856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777913856,
777914112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777914112,
777916160
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777916160,
777921280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777921280,
777921536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777921536,
777929728
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777929728,
777931776
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777931776,
777936896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777936896,
777942016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777942016,
777961472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
777961472,
777980928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
777980928,
777986048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777986048,
777986304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
777986304,
777988352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
777988352,
777993472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
777993472,
777993728
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
777993728,
778001920
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778001920,
778003968
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778003968,
778009088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778009088,
778014208
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778014208,
778033664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778033664,
778053120
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778053120,
778058240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778058240,
778058496
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778058496,
778060544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778060544,
778065664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778065664,
778065920
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778065920,
778074112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778074112,
778076160
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778076160,
778081280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778081280,
778086400
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778086400,
778105856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778105856,
778125312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778125312,
778130432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778130432,
778130688
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778130688,
778132736
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778132736,
778137856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778137856,
778138112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778138112,
778146304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778146304,
778148352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778148352,
778153472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778153472,
778158592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778158592,
778178048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778178048,
778197504
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778197504,
778202624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778202624,
778202880
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778202880,
778204928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778204928,
778210048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778210048,
778210304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778210304,
778218496
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778218496,
778220544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778220544,
778225664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778225664,
778230784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778230784,
778250240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778250240,
778269696
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778269696,
778274816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778274816,
778275072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778275072,
778277120
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778277120,
778282240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778282240,
778282496
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778282496,
778290688
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778290688,
778292736
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778292736,
778297856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778297856,
778302976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778302976,
778322432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778322432,
778341888
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778341888,
778347008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778347008,
778347264
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778347264,
778349312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778349312,
778354432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778354432,
778354688
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778354688,
778362880
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778362880,
778364928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778364928,
778370048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778370048,
778375168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778375168,
778394624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778394624,
778414080
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778414080,
778419200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778419200,
778419456
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778419456,
778421504
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778421504,
778426624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778426624,
778426880
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778426880,
778435072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778435072,
778437120
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778437120,
778442240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778442240,
778447360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778447360,
778466816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778466816,
778486272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778486272,
778491392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778491392,
778491648
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778491648,
778493696
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778493696,
778498816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778498816,
778499072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778499072,
778507264
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778507264,
778509312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778509312,
778514432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778514432,
778519552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778519552,
778539008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778539008,
778558464
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778558464,
778563584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778563584,
778563840
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778563840,
778565888
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778565888,
778571008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778571008,
778571264
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778571264,
778579456
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778579456,
778581504
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778581504,
778600960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778600960,
778620416
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778620416,
778620672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778620672,
778622720
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778622720,
778627840
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778627840,
778628096
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778628096,
778636288
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778636288,
778638336
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778638336,
778643456
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778643456,
778648576
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778648576,
778668032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778668032,
778687488
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778687488,
778692608
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778692608,
778692864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778692864,
778694912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778694912,
778700032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778700032,
778700288
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778700288,
778708480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778708480,
778710528
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778710528,
778715648
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778715648,
778720768
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778720768,
778740224
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778740224,
778759680
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778759680,
778764800
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778764800,
778765056
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778765056,
778767104
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778767104,
778772224
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778772224,
778772480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778772480,
778780672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778780672,
778782720
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778782720,
778787840
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778787840,
778792960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778792960,
778812416
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778812416,
778831872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778831872,
778836992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778836992,
778837248
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778837248,
778839296
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778839296,
778844416
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778844416,
778844672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778844672,
778852864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778852864,
778854912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778854912,
778860032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778860032,
778865152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778865152,
778884608
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778884608,
778904064
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778904064,
778909184
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778909184,
778909440
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778909440,
778911488
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778911488,
778916608
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778916608,
778916864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778916864,
778925056
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778925056,
778927104
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778927104,
778932224
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778932224,
778937344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778937344,
778956800
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
778956800,
778976256
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778976256,
778981376
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778981376,
778981632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778981632,
778983680
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
778983680,
778988800
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
778988800,
778989056
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
778989056,
778997248
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
778997248,
778999296
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
778999296,
779004416
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
779004416,
779009536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
779009536,
779028992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
779028992,
779048448
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
779048448,
779053568
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
779053568,
779053824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
779053824,
779055872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
779055872,
779060992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
779060992,
779061248
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
779061248,
779069440
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
779069440,
779071488
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
779071488,
779073536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
779073536,
781170688
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
781170688,
781176832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
781176832,
787468288
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
787468288,
787476480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
787476480,
795865088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
795865088,
795867136
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
795867136,
804255744
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
804255744,
804257792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
804257792,
804259840
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
804259840,
804261888
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.0.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
804261888,
804263936
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
804263936,
804265984
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
804265984,
806363136
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
806363136,
806369280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
806369280,
812660736
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
812660736,
812668928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
812668928,
821057536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
821057536,
821059584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
821059584,
829448192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
829448192,
829450240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
829450240,
829452288
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
829452288,
829454336
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.1.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
829454336,
829456384
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
829456384,
829458432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
829458432,
831555584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
831555584,
831561728
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
831561728,
837853184
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
837853184,
837861376
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
837861376,
846249984
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
846249984,
846252032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
846252032,
854640640
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
854640640,
854642688
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
854642688,
854644736
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
854644736,
854646784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.10.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
854646784,
854648832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
854648832,
854650880
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
854650880,
856748032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
856748032,
856754176
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
856754176,
863045632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
863045632,
863053824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
863053824,
871442432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
871442432,
871444480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
871444480,
879833088
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
879833088,
879835136
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
879835136,
879837184
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
879837184,
879839232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.11.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
879839232,
879841280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
879841280,
879843328
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
879843328,
881940480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
881940480,
881946624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
881946624,
888238080
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
888238080,
888246272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
888246272,
896634880
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
896634880,
896636928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
896636928,
905025536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
905025536,
905027584
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
905027584,
905029632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
905029632,
905031680
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.12.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
905031680,
905033728
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
905033728,
905035776
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
905035776,
907132928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
907132928,
907139072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
907139072,
913430528
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
913430528,
913438720
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
913438720,
921827328
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
921827328,
921829376
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
921829376,
930217984
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
930217984,
930220032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
930220032,
930222080
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
930222080,
930224128
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.13.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
930224128,
930226176
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
930226176,
930228224
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
930228224,
932325376
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
932325376,
932331520
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
932331520,
938622976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
938622976,
938631168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
938631168,
947019776
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
947019776,
947021824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
947021824,
955410432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
955410432,
955412480
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
955412480,
955414528
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
955414528,
955416576
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.14.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
955416576,
955418624
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
955418624,
955420672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
955420672,
957517824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
957517824,
957523968
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
957523968,
963815424
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
963815424,
963823616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
963823616,
972212224
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
972212224,
972214272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
972214272,
980602880
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
980602880,
980604928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
980604928,
980606976
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
980606976,
980609024
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.15.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
980609024,
980611072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
980611072,
980613120
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
980613120,
982710272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
982710272,
982716416
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
982716416,
989007872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
989007872,
989016064
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
989016064,
997404672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
997404672,
997406720
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
997406720,
1005795328
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1005795328,
1005797376
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1005797376,
1005799424
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1005799424,
1005801472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.16.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1005801472,
1005803520
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1005803520,
1005805568
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1005805568,
1007902720
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1007902720,
1007908864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1007908864,
1014200320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1014200320,
1014208512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1014208512,
1022597120
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1022597120,
1022599168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1022599168,
1030987776
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1030987776,
1030989824
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1030989824,
1030991872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1030991872,
1030993920
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.17.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1030993920,
1030995968
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1030995968,
1030998016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1030998016,
1033095168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1033095168,
1033101312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1033101312,
1039392768
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1039392768,
1039400960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1039400960,
1047789568
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1047789568,
1047791616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1047791616,
1056180224
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1056180224,
1056182272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1056182272,
1056184320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1056184320,
1056186368
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.18.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1056186368,
1056188416
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1056188416,
1056190464
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1056190464,
1058287616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1058287616,
1058293760
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1058293760,
1064585216
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1064585216,
1064593408
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1064593408,
1072982016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1072982016,
1072984064
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1072984064,
1081372672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1081372672,
1081374720
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1081374720,
1081376768
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1081376768,
1081378816
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.19.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1081378816,
1081380864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1081380864,
1081382912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1081382912,
1083480064
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1083480064,
1083486208
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1083486208,
1089777664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1089777664,
1089785856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1089785856,
1098174464
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1098174464,
1098176512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1098176512,
1106565120
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1106565120,
1106567168
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1106567168,
1106569216
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1106569216,
1106571264
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.2.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1106571264,
1106573312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1106573312,
1106575360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1106575360,
1108672512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1108672512,
1108678656
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1108678656,
1114970112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1114970112,
1114978304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1114978304,
1123366912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1123366912,
1123368960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1123368960,
1131757568
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1131757568,
1131759616
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1131759616,
1131761664
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1131761664,
1131763712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.20.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1131763712,
1131765760
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1131765760,
1131767808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1131767808,
1133864960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1133864960,
1133871104
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1133871104,
1140162560
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1140162560,
1140170752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1140170752,
1148559360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1148559360,
1148561408
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1148561408,
1156950016
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1156950016,
1156952064
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1156952064,
1156954112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1156954112,
1156956160
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.21.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1156956160,
1156958208
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1156958208,
1156960256
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1156960256,
1159057408
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1159057408,
1159063552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1159063552,
1165355008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1165355008,
1165363200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1165363200,
1173751808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1173751808,
1173753856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1173753856,
1182142464
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1182142464,
1182144512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1182144512,
1182146560
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1182146560,
1182148608
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.22.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1182148608,
1182150656
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1182150656,
1182152704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1182152704,
1184249856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1184249856,
1184256000
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1184256000,
1190547456
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1190547456,
1190555648
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1190555648,
1198944256
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1198944256,
1198946304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1198946304,
1207334912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1207334912,
1207336960
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1207336960,
1207339008
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1207339008,
1207341056
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.23.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1207341056,
1207343104
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1207343104,
1207345152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1207345152,
1209442304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1209442304,
1209448448
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1209448448,
1215739904
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1215739904,
1215748096
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1215748096,
1224136704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1224136704,
1224138752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1224138752,
1232527360
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1232527360,
1232529408
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1232529408,
1232531456
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1232531456,
1232533504
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.3.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1232533504,
1232535552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1232535552,
1232537600
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1232537600,
1234634752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1234634752,
1234640896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1234640896,
1240932352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1240932352,
1240940544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1240940544,
1249329152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1249329152,
1249331200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1249331200,
1257719808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1257719808,
1257721856
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1257721856,
1257723904
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1257723904,
1257725952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.4.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1257725952,
1257728000
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1257728000,
1257730048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1257730048,
1259827200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1259827200,
1259833344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1259833344,
1266124800
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1266124800,
1266132992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1266132992,
1274521600
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1274521600,
1274523648
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1274523648,
1282912256
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1282912256,
1282914304
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1282914304,
1282916352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1282916352,
1282918400
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.5.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1282918400,
1282920448
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1282920448,
1282922496
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1282922496,
1285019648
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1285019648,
1285025792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1285025792,
1291317248
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1291317248,
1291325440
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1291325440,
1299714048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1299714048,
1299716096
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1299716096,
1308104704
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1308104704,
1308106752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1308106752,
1308108800
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1308108800,
1308110848
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.6.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1308110848,
1308112896
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1308112896,
1308114944
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1308114944,
1310212096
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1310212096,
1310218240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1310218240,
1316509696
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1316509696,
1316517888
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1316517888,
1324906496
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1324906496,
1324908544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1324908544,
1333297152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1333297152,
1333299200
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1333299200,
1333301248
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1333301248,
1333303296
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.7.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1333303296,
1333305344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1333305344,
1333307392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1333307392,
1335404544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1335404544,
1335410688
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1335410688,
1341702144
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1341702144,
1341710336
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1341710336,
1350098944
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1350098944,
1350100992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1350100992,
1358489600
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1358489600,
1358491648
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1358491648,
1358493696
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1358493696,
1358495744
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.8.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1358495744,
1358497792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.attn.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1358497792,
1358499840
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.attn.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
1024
],
"data_offsets": [
1358499840,
1360596992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.attn.qkv.bias": {
"dtype": "BF16",
"shape": [
3072
],
"data_offsets": [
1360596992,
1360603136
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.attn.qkv.weight": {
"dtype": "BF16",
"shape": [
3072,
1024
],
"data_offsets": [
1360603136,
1366894592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.mlp.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1366894592,
1366902784
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.mlp.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
1024
],
"data_offsets": [
1366902784,
1375291392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.mlp.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1375291392,
1375293440
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.mlp.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
1024,
4096
],
"data_offsets": [
1375293440,
1383682048
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.norm1.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1383682048,
1383684096
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.norm1.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1383684096,
1383686144
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.norm2.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1383686144,
1383688192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.blocks.9.norm2.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1383688192,
1383690240
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.0.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1383690240,
1383698432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.0.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
4096
],
"data_offsets": [
1383698432,
1417252864
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.0.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
1417252864,
1417257984
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.0.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
2560,
4096
],
"data_offsets": [
1417257984,
1438229504
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.0.norm.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1438229504,
1438237696
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.0.norm.weight": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1438237696,
1438245888
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.1.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1438245888,
1438254080
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.1.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
4096
],
"data_offsets": [
1438254080,
1471808512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.1.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
1471808512,
1471813632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.1.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
2560,
4096
],
"data_offsets": [
1471813632,
1492785152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.1.norm.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1492785152,
1492793344
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.1.norm.weight": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1492793344,
1492801536
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.2.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1492801536,
1492809728
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.2.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
4096
],
"data_offsets": [
1492809728,
1526364160
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.2.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
1526364160,
1526369280
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.2.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
2560,
4096
],
"data_offsets": [
1526369280,
1547340800
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.2.norm.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1547340800,
1547348992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.deepstack_merger_list.2.norm.weight": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1547348992,
1547357184
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.merger.linear_fc1.bias": {
"dtype": "BF16",
"shape": [
4096
],
"data_offsets": [
1547357184,
1547365376
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.merger.linear_fc1.weight": {
"dtype": "BF16",
"shape": [
4096,
4096
],
"data_offsets": [
1547365376,
1580919808
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.merger.linear_fc2.bias": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
1580919808,
1580924928
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.merger.linear_fc2.weight": {
"dtype": "BF16",
"shape": [
2560,
4096
],
"data_offsets": [
1580924928,
1601896448
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.merger.norm.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1601896448,
1601898496
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.merger.norm.weight": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1601898496,
1601900544
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.patch_embed.proj.bias": {
"dtype": "BF16",
"shape": [
1024
],
"data_offsets": [
1601900544,
1601902592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.patch_embed.proj.weight": {
"dtype": "BF16",
"shape": [
1024,
3,
2,
16,
16
],
"data_offsets": [
1601902592,
1605048320
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.visual.pos_embed.weight": {
"dtype": "BF16",
"shape": [
2304,
1024
],
"data_offsets": [
1605048320,
1609766912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
1609766912,
1634670592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1634670592,
1659574272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1659574272,
1684477952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1684477952,
1687099392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
1687099392,
1697585152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
1697585152,
1708070912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.0.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1708070912,
1710692352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
1710692352,
1735596032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1735596032,
1760499712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1760499712,
1785403392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1785403392,
1788024832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
1788024832,
1798510592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
1798510592,
1808996352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.1.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1808996352,
1811617792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
1811617792,
1836521472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1836521472,
1861425152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1861425152,
1886328832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1886328832,
1888950272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
1888950272,
1899436032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
1899436032,
1909921792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.10.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1909921792,
1912543232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
1912543232,
1937446912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1937446912,
1962350592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
1962350592,
1987254272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1987254272,
1989875712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
1989875712,
2000361472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2000361472,
2010847232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.11.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2010847232,
2013468672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2013468672,
2038372352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2038372352,
2063276032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2063276032,
2088179712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2088179712,
2090801152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2090801152,
2101286912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2101286912,
2111772672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.12.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2111772672,
2114394112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2114394112,
2139297792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2139297792,
2164201472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2164201472,
2189105152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2189105152,
2191726592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2191726592,
2202212352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2202212352,
2212698112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.13.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2212698112,
2215319552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2215319552,
2240223232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2240223232,
2265126912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2265126912,
2290030592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2290030592,
2292652032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2292652032,
2303137792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2303137792,
2313623552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.14.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2313623552,
2316244992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2316244992,
2341148672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2341148672,
2366052352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2366052352,
2390956032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2390956032,
2393577472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2393577472,
2404063232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2404063232,
2414548992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.15.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2414548992,
2417170432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2417170432,
2442074112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2442074112,
2466977792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2466977792,
2491881472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2491881472,
2494502912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2494502912,
2504988672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2504988672,
2515474432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.16.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2515474432,
2518095872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2518095872,
2542999552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2542999552,
2567903232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2567903232,
2592806912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2592806912,
2595428352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2595428352,
2605914112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2605914112,
2616399872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.17.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2616399872,
2619021312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2619021312,
2643924992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2643924992,
2668828672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2668828672,
2693732352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2693732352,
2696353792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2696353792,
2706839552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2706839552,
2717325312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.18.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2717325312,
2719946752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2719946752,
2744850432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2744850432,
2769754112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2769754112,
2794657792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2794657792,
2797279232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2797279232,
2807764992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2807764992,
2818250752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.19.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2818250752,
2820872192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2820872192,
2845775872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2845775872,
2870679552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2870679552,
2895583232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2895583232,
2898204672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2898204672,
2908690432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
2908690432,
2919176192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.2.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2919176192,
2921797632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
2921797632,
2946701312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2946701312,
2971604992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
2971604992,
2996508672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
2996508672,
2999130112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
2999130112,
3009615872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3009615872,
3020101632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.20.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3020101632,
3022723072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3022723072,
3047626752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3047626752,
3072530432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3072530432,
3097434112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3097434112,
3100055552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3100055552,
3110541312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3110541312,
3121027072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.21.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3121027072,
3123648512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3123648512,
3148552192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3148552192,
3173455872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3173455872,
3198359552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3198359552,
3200980992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3200980992,
3211466752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3211466752,
3221952512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.22.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3221952512,
3224573952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3224573952,
3249477632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3249477632,
3274381312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3274381312,
3299284992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3299284992,
3301906432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3301906432,
3312392192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3312392192,
3322877952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.23.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3322877952,
3325499392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3325499392,
3350403072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3350403072,
3375306752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3375306752,
3400210432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3400210432,
3402831872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3402831872,
3413317632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3413317632,
3423803392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.24.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3423803392,
3426424832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3426424832,
3451328512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3451328512,
3476232192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3476232192,
3501135872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3501135872,
3503757312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3503757312,
3514243072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3514243072,
3524728832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.25.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3524728832,
3527350272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3527350272,
3552253952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3552253952,
3577157632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3577157632,
3602061312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3602061312,
3604682752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3604682752,
3615168512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3615168512,
3625654272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.26.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3625654272,
3628275712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3628275712,
3653179392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3653179392,
3678083072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3678083072,
3702986752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3702986752,
3705608192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3705608192,
3716093952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3716093952,
3726579712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.27.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3726579712,
3729201152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3729201152,
3754104832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3754104832,
3779008512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3779008512,
3803912192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3803912192,
3806533632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3806533632,
3817019392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3817019392,
3827505152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.28.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3827505152,
3830126592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3830126592,
3855030272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3855030272,
3879933952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3879933952,
3904837632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3904837632,
3907459072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
3907459072,
3917944832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
3917944832,
3928430592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.29.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
3928430592,
3931052032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
3931052032,
3955955712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3955955712,
3980859392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
3980859392,
4005763072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4005763072,
4008384512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4008384512,
4018870272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4018870272,
4029356032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.3.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4029356032,
4031977472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4031977472,
4056881152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4056881152,
4081784832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4081784832,
4106688512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4106688512,
4109309952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4109309952,
4119795712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4119795712,
4130281472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.30.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4130281472,
4132902912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4132902912,
4157806592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4157806592,
4182710272
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4182710272,
4207613952
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4207613952,
4210235392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4210235392,
4220721152
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4220721152,
4231206912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.31.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4231206912,
4233828352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4233828352,
4258732032
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4258732032,
4283635712
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4283635712,
4308539392
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4308539392,
4311160832
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4311160832,
4321646592
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4321646592,
4332132352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.32.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4332132352,
4334753792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4334753792,
4359657472
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4359657472,
4362278912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4362278912,
4372764672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4372764672,
4383250432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.33.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4383250432,
4385871872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4385871872,
4410775552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4410775552,
4435679232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4435679232,
4460582912
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4460582912,
4463204352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4463204352,
4473690112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4473690112,
4484175872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.4.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4484175872,
4486797312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4486797312,
4511700992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4511700992,
4536604672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4536604672,
4561508352
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4561508352,
4564129792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4564129792,
4574615552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4574615552,
4585101312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.5.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4585101312,
4587722752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4587722752,
4612626432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4612626432,
4637530112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4637530112,
4662433792
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4662433792,
4665055232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4665055232,
4675540992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4675540992,
4686026752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.6.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4686026752,
4688648192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4688648192,
4713551872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4713551872,
4738455552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4738455552,
4763359232
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4763359232,
4765980672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4765980672,
4776466432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4776466432,
4786952192
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.7.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4786952192,
4789573632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4789573632,
4814477312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4814477312,
4839380992
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4839380992,
4864284672
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4864284672,
4866906112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4866906112,
4877391872
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4877391872,
4887877632
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.8.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4887877632,
4890499072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
4890499072,
4915402752
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4915402752,
4940306432
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
4940306432,
4965210112
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4965210112,
4967831552
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
4967831552,
4978317312
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
4978317312,
4988803072
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"model.language_model.layers.9.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
4988803072,
4991424512
],
"file": "model-00001-of-00002.safetensors",
"payload_start": 115872
},
"lm_head.weight": {
"dtype": "BF16",
"shape": [
151686,
2560
],
"data_offsets": [
0,
776632320
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.33.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776632320,
776637440
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.33.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776637440,
776642560
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.33.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776642560,
776647680
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776647680,
776652800
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776652800,
776657920
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776657920,
776677376
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776677376,
776696832
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776696832,
776701952
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776701952,
776702208
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776702208,
776704256
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776704256,
776709376
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776709376,
776709632
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776709632,
776717824
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776717824,
776719872
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.input_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776719872,
776724992
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.mlp.down_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776724992,
776730112
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.mlp.gate_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776730112,
776749568
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.mlp.up_proj.weight_scale": {
"dtype": "BF16",
"shape": [
9728,
1
],
"data_offsets": [
776749568,
776769024
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.post_attention_layernorm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776769024,
776774144
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.k_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776774144,
776774400
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.k_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776774400,
776776448
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.o_proj.weight_scale": {
"dtype": "BF16",
"shape": [
2560,
1
],
"data_offsets": [
776776448,
776781568
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.q_norm.weight": {
"dtype": "BF16",
"shape": [
128
],
"data_offsets": [
776781568,
776781824
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.q_proj.weight_scale": {
"dtype": "BF16",
"shape": [
4096,
1
],
"data_offsets": [
776781824,
776790016
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.v_proj.weight_scale": {
"dtype": "BF16",
"shape": [
1024,
1
],
"data_offsets": [
776790016,
776792064
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.norm.weight": {
"dtype": "BF16",
"shape": [
2560
],
"data_offsets": [
776792064,
776797184
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.33.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
776797184,
801700864
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.33.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
801700864,
826604544
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
826604544,
851508224
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
851508224,
876411904
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
876411904,
901315584
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
901315584,
903937024
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
903937024,
914422784
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
914422784,
924908544
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.34.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
924908544,
927529984
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.mlp.down_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
9728
],
"data_offsets": [
927529984,
952433664
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.mlp.gate_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
952433664,
977337344
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.mlp.up_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
9728,
2560
],
"data_offsets": [
977337344,
1002241024
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.k_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1002241024,
1004862464
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.o_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
2560,
4096
],
"data_offsets": [
1004862464,
1015348224
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.q_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
4096,
2560
],
"data_offsets": [
1015348224,
1025833984
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
},
"model.language_model.layers.35.self_attn.v_proj.weight": {
"dtype": "F8_E4M3",
"shape": [
1024,
2560
],
"data_offsets": [
1025833984,
1028455424
],
"file": "model-00002-of-00002.safetensors",
"payload_start": 5616
}
},
"activation_contract": "dynamic per-token FP8 inputs to decoder projections; BF16 residual/vision/head",
"activation_caveat": "Static tensor audit cannot prove runtime kernel dispatch; vLLM reload is separately required."
}