bf16 build of MOSS-Image (SFT)

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 4bit/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 6bit/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 8bit/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+bf16/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

bf16/mflux_model.json

@@ -0,0 +1,20 @@
+{
+  "format_version": 1,
+  "mflux_version": "0.24.0",
+  "created_at": "2026-11-12T09:40:44Z",
+  "updated_at": "2026-11-12T09:40:44Z",
+  "model_name": "OpenMOSS-Team__MOSS-Image-SFT",
+  "base_model": "moss-image-sft",
+  "quantize": null,
+  "size_gb": 26.18,
+  "upstream": {
+    "repo_id": null,
+    "revision": null,
+    "revision_date": null,
+    "size_gb": 27.23
+  },
+  "text_encoders": [
+    "qwen3_5"
+  ],
+  "loras": []
+}

bf16/text_encoder/0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be8575f99787ede2b79745db10246a1ffdcf376c996a38e444daa96a0db0344
+size 2134967460

bf16/text_encoder/1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76826c2512c5a4890147807b65383573344d42fc10065a0681fad95963c3928f
+size 2099602996

bf16/text_encoder/2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d143078bfed0d4ac8c8280ca0a8fe592e73b0210490f1bf45406c4f3be8c108b
+size 2133157389

bf16/text_encoder/3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86de523b1bb77c63015810f9b3840b933927c7c8846a26673643d06deb3f42ac
+size 2065965719

bf16/text_encoder/4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf868fb3c3465bd2f9659672903c25fc94d5005eaf73776f7aa63a608afa5e0
+size 2048681892

bf16/text_encoder/5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b728c34f6c49d9ac859e925efa6ba41cfe7264d54f117d62b41cd5225f37d5
+size 2066048651

bf16/text_encoder/6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab6019f987bb465ff6c7c05531d6ad14809f84f4046677591596b755a3cb5cc
+size 2132632984

bf16/text_encoder/7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e67006774cff3baf6a9d9b02afc10a818303e9854abb54e25b7406aad55d445
+size 1192358948

bf16/text_encoder/model.safetensors.index.json

@@ -0,0 +1,434 @@
+{
+  "metadata": {
+    "quantization_level": "None",
+    "mflux_version": "0.24.0"
+  },
+  "weight_map": {
+    "embed_tokens.weight": "0.safetensors",
+    "layers.0.linear_attn.conv1d.weight": "0.safetensors",
+    "layers.0.linear_attn.dt_bias": "0.safetensors",
+    "layers.0.linear_attn.A_log": "0.safetensors",
+    "layers.0.linear_attn.norm.weight": "0.safetensors",
+    "layers.0.linear_attn.out_proj.weight": "0.safetensors",
+    "layers.0.linear_attn.in_proj_qkv.weight": "0.safetensors",
+    "layers.0.linear_attn.in_proj_z.weight": "1.safetensors",
+    "layers.0.linear_attn.in_proj_b.weight": "1.safetensors",
+    "layers.0.linear_attn.in_proj_a.weight": "1.safetensors",
+    "layers.0.mlp.gate_proj.weight": "1.safetensors",
+    "layers.0.mlp.up_proj.weight": "1.safetensors",
+    "layers.0.mlp.down_proj.weight": "1.safetensors",
+    "layers.0.input_layernorm.weight": "1.safetensors",
+    "layers.0.post_attention_layernorm.weight": "1.safetensors",
+    "layers.1.linear_attn.conv1d.weight": "1.safetensors",
+    "layers.1.linear_attn.dt_bias": "1.safetensors",
+    "layers.1.linear_attn.A_log": "1.safetensors",
+    "layers.1.linear_attn.norm.weight": "1.safetensors",
+    "layers.1.linear_attn.out_proj.weight": "1.safetensors",
+    "layers.1.linear_attn.in_proj_qkv.weight": "1.safetensors",
+    "layers.1.linear_attn.in_proj_z.weight": "1.safetensors",
+    "layers.1.linear_attn.in_proj_b.weight": "1.safetensors",
+    "layers.1.linear_attn.in_proj_a.weight": "1.safetensors",
+    "layers.1.mlp.gate_proj.weight": "1.safetensors",
+    "layers.1.mlp.up_proj.weight": "1.safetensors",
+    "layers.1.mlp.down_proj.weight": "1.safetensors",
+    "layers.1.input_layernorm.weight": "1.safetensors",
+    "layers.1.post_attention_layernorm.weight": "1.safetensors",
+    "layers.2.linear_attn.conv1d.weight": "1.safetensors",
+    "layers.2.linear_attn.dt_bias": "1.safetensors",
+    "layers.2.linear_attn.A_log": "1.safetensors",
+    "layers.2.linear_attn.norm.weight": "1.safetensors",
+    "layers.2.linear_attn.out_proj.weight": "1.safetensors",
+    "layers.2.linear_attn.in_proj_qkv.weight": "1.safetensors",
+    "layers.2.linear_attn.in_proj_z.weight": "1.safetensors",
+    "layers.2.linear_attn.in_proj_b.weight": "1.safetensors",
+    "layers.2.linear_attn.in_proj_a.weight": "1.safetensors",
+    "layers.2.mlp.gate_proj.weight": "1.safetensors",
+    "layers.2.mlp.up_proj.weight": "1.safetensors",
+    "layers.2.mlp.down_proj.weight": "1.safetensors",
+    "layers.2.input_layernorm.weight": "1.safetensors",
+    "layers.2.post_attention_layernorm.weight": "1.safetensors",
+    "layers.3.self_attn.q_proj.weight": "1.safetensors",
+    "layers.3.self_attn.k_proj.weight": "1.safetensors",
+    "layers.3.self_attn.v_proj.weight": "1.safetensors",
+    "layers.3.self_attn.o_proj.weight": "1.safetensors",
+    "layers.3.self_attn.q_norm.weight": "1.safetensors",
+    "layers.3.self_attn.k_norm.weight": "1.safetensors",
+    "layers.3.mlp.gate_proj.weight": "1.safetensors",
+    "layers.3.mlp.up_proj.weight": "1.safetensors",
+    "layers.3.mlp.down_proj.weight": "1.safetensors",
+    "layers.3.input_layernorm.weight": "1.safetensors",
+    "layers.3.post_attention_layernorm.weight": "1.safetensors",
+    "layers.4.linear_attn.conv1d.weight": "1.safetensors",
+    "layers.4.linear_attn.dt_bias": "1.safetensors",
+    "layers.4.linear_attn.A_log": "1.safetensors",
+    "layers.4.linear_attn.norm.weight": "1.safetensors",
+    "layers.4.linear_attn.out_proj.weight": "1.safetensors",
+    "layers.4.linear_attn.in_proj_qkv.weight": "1.safetensors",
+    "layers.4.linear_attn.in_proj_z.weight": "1.safetensors",
+    "layers.4.linear_attn.in_proj_b.weight": "1.safetensors",
+    "layers.4.linear_attn.in_proj_a.weight": "1.safetensors",
+    "layers.4.mlp.gate_proj.weight": "1.safetensors",
+    "layers.4.mlp.up_proj.weight": "1.safetensors",
+    "layers.4.mlp.down_proj.weight": "1.safetensors",
+    "layers.4.input_layernorm.weight": "1.safetensors",
+    "layers.4.post_attention_layernorm.weight": "1.safetensors",
+    "layers.5.linear_attn.conv1d.weight": "1.safetensors",
+    "layers.5.linear_attn.dt_bias": "1.safetensors",
+    "layers.5.linear_attn.A_log": "1.safetensors",
+    "layers.5.linear_attn.norm.weight": "1.safetensors",
+    "layers.5.linear_attn.out_proj.weight": "1.safetensors",
+    "layers.5.linear_attn.in_proj_qkv.weight": "2.safetensors",
+    "layers.5.linear_attn.in_proj_z.weight": "2.safetensors",
+    "layers.5.linear_attn.in_proj_b.weight": "2.safetensors",
+    "layers.5.linear_attn.in_proj_a.weight": "2.safetensors",
+    "layers.5.mlp.gate_proj.weight": "2.safetensors",
+    "layers.5.mlp.up_proj.weight": "2.safetensors",
+    "layers.5.mlp.down_proj.weight": "2.safetensors",
+    "layers.5.input_layernorm.weight": "2.safetensors",
+    "layers.5.post_attention_layernorm.weight": "2.safetensors",
+    "layers.6.linear_attn.conv1d.weight": "2.safetensors",
+    "layers.6.linear_attn.dt_bias": "2.safetensors",
+    "layers.6.linear_attn.A_log": "2.safetensors",
+    "layers.6.linear_attn.norm.weight": "2.safetensors",
+    "layers.6.linear_attn.out_proj.weight": "2.safetensors",
+    "layers.6.linear_attn.in_proj_qkv.weight": "2.safetensors",
+    "layers.6.linear_attn.in_proj_z.weight": "2.safetensors",
+    "layers.6.linear_attn.in_proj_b.weight": "2.safetensors",
+    "layers.6.linear_attn.in_proj_a.weight": "2.safetensors",
+    "layers.6.mlp.gate_proj.weight": "2.safetensors",
+    "layers.6.mlp.up_proj.weight": "2.safetensors",
+    "layers.6.mlp.down_proj.weight": "2.safetensors",
+    "layers.6.input_layernorm.weight": "2.safetensors",
+    "layers.6.post_attention_layernorm.weight": "2.safetensors",
+    "layers.7.self_attn.q_proj.weight": "2.safetensors",
+    "layers.7.self_attn.k_proj.weight": "2.safetensors",
+    "layers.7.self_attn.v_proj.weight": "2.safetensors",
+    "layers.7.self_attn.o_proj.weight": "2.safetensors",
+    "layers.7.self_attn.q_norm.weight": "2.safetensors",
+    "layers.7.self_attn.k_norm.weight": "2.safetensors",
+    "layers.7.mlp.gate_proj.weight": "2.safetensors",
+    "layers.7.mlp.up_proj.weight": "2.safetensors",
+    "layers.7.mlp.down_proj.weight": "2.safetensors",
+    "layers.7.input_layernorm.weight": "2.safetensors",
+    "layers.7.post_attention_layernorm.weight": "2.safetensors",
+    "layers.8.linear_attn.conv1d.weight": "2.safetensors",
+    "layers.8.linear_attn.dt_bias": "2.safetensors",
+    "layers.8.linear_attn.A_log": "2.safetensors",
+    "layers.8.linear_attn.norm.weight": "2.safetensors",
+    "layers.8.linear_attn.out_proj.weight": "2.safetensors",
+    "layers.8.linear_attn.in_proj_qkv.weight": "2.safetensors",
+    "layers.8.linear_attn.in_proj_z.weight": "2.safetensors",
+    "layers.8.linear_attn.in_proj_b.weight": "2.safetensors",
+    "layers.8.linear_attn.in_proj_a.weight": "2.safetensors",
+    "layers.8.mlp.gate_proj.weight": "2.safetensors",
+    "layers.8.mlp.up_proj.weight": "2.safetensors",
+    "layers.8.mlp.down_proj.weight": "2.safetensors",
+    "layers.8.input_layernorm.weight": "2.safetensors",
+    "layers.8.post_attention_layernorm.weight": "2.safetensors",
+    "layers.9.linear_attn.conv1d.weight": "2.safetensors",
+    "layers.9.linear_attn.dt_bias": "2.safetensors",
+    "layers.9.linear_attn.A_log": "2.safetensors",
+    "layers.9.linear_attn.norm.weight": "2.safetensors",
+    "layers.9.linear_attn.out_proj.weight": "2.safetensors",
+    "layers.9.linear_attn.in_proj_qkv.weight": "2.safetensors",
+    "layers.9.linear_attn.in_proj_z.weight": "2.safetensors",
+    "layers.9.linear_attn.in_proj_b.weight": "2.safetensors",
+    "layers.9.linear_attn.in_proj_a.weight": "2.safetensors",
+    "layers.9.mlp.gate_proj.weight": "2.safetensors",
+    "layers.9.mlp.up_proj.weight": "2.safetensors",
+    "layers.9.mlp.down_proj.weight": "2.safetensors",
+    "layers.9.input_layernorm.weight": "2.safetensors",
+    "layers.9.post_attention_layernorm.weight": "2.safetensors",
+    "layers.10.linear_attn.conv1d.weight": "2.safetensors",
+    "layers.10.linear_attn.dt_bias": "2.safetensors",
+    "layers.10.linear_attn.A_log": "2.safetensors",
+    "layers.10.linear_attn.norm.weight": "2.safetensors",
+    "layers.10.linear_attn.out_proj.weight": "3.safetensors",
+    "layers.10.linear_attn.in_proj_qkv.weight": "3.safetensors",
+    "layers.10.linear_attn.in_proj_z.weight": "3.safetensors",
+    "layers.10.linear_attn.in_proj_b.weight": "3.safetensors",
+    "layers.10.linear_attn.in_proj_a.weight": "3.safetensors",
+    "layers.10.mlp.gate_proj.weight": "3.safetensors",
+    "layers.10.mlp.up_proj.weight": "3.safetensors",
+    "layers.10.mlp.down_proj.weight": "3.safetensors",
+    "layers.10.input_layernorm.weight": "3.safetensors",
+    "layers.10.post_attention_layernorm.weight": "3.safetensors",
+    "layers.11.self_attn.q_proj.weight": "3.safetensors",
+    "layers.11.self_attn.k_proj.weight": "3.safetensors",
+    "layers.11.self_attn.v_proj.weight": "3.safetensors",
+    "layers.11.self_attn.o_proj.weight": "3.safetensors",
+    "layers.11.self_attn.q_norm.weight": "3.safetensors",
+    "layers.11.self_attn.k_norm.weight": "3.safetensors",
+    "layers.11.mlp.gate_proj.weight": "3.safetensors",
+    "layers.11.mlp.up_proj.weight": "3.safetensors",
+    "layers.11.mlp.down_proj.weight": "3.safetensors",
+    "layers.11.input_layernorm.weight": "3.safetensors",
+    "layers.11.post_attention_layernorm.weight": "3.safetensors",
+    "layers.12.linear_attn.conv1d.weight": "3.safetensors",
+    "layers.12.linear_attn.dt_bias": "3.safetensors",
+    "layers.12.linear_attn.A_log": "3.safetensors",
+    "layers.12.linear_attn.norm.weight": "3.safetensors",
+    "layers.12.linear_attn.out_proj.weight": "3.safetensors",
+    "layers.12.linear_attn.in_proj_qkv.weight": "3.safetensors",
+    "layers.12.linear_attn.in_proj_z.weight": "3.safetensors",
+    "layers.12.linear_attn.in_proj_b.weight": "3.safetensors",
+    "layers.12.linear_attn.in_proj_a.weight": "3.safetensors",
+    "layers.12.mlp.gate_proj.weight": "3.safetensors",
+    "layers.12.mlp.up_proj.weight": "3.safetensors",
+    "layers.12.mlp.down_proj.weight": "3.safetensors",
+    "layers.12.input_layernorm.weight": "3.safetensors",
+    "layers.12.post_attention_layernorm.weight": "3.safetensors",
+    "layers.13.linear_attn.conv1d.weight": "3.safetensors",
+    "layers.13.linear_attn.dt_bias": "3.safetensors",
+    "layers.13.linear_attn.A_log": "3.safetensors",
+    "layers.13.linear_attn.norm.weight": "3.safetensors",
+    "layers.13.linear_attn.out_proj.weight": "3.safetensors",
+    "layers.13.linear_attn.in_proj_qkv.weight": "3.safetensors",
+    "layers.13.linear_attn.in_proj_z.weight": "3.safetensors",
+    "layers.13.linear_attn.in_proj_b.weight": "3.safetensors",
+    "layers.13.linear_attn.in_proj_a.weight": "3.safetensors",
+    "layers.13.mlp.gate_proj.weight": "3.safetensors",
+    "layers.13.mlp.up_proj.weight": "3.safetensors",
+    "layers.13.mlp.down_proj.weight": "3.safetensors",
+    "layers.13.input_layernorm.weight": "3.safetensors",
+    "layers.13.post_attention_layernorm.weight": "3.safetensors",
+    "layers.14.linear_attn.conv1d.weight": "3.safetensors",
+    "layers.14.linear_attn.dt_bias": "3.safetensors",
+    "layers.14.linear_attn.A_log": "3.safetensors",
+    "layers.14.linear_attn.norm.weight": "3.safetensors",
+    "layers.14.linear_attn.out_proj.weight": "3.safetensors",
+    "layers.14.linear_attn.in_proj_qkv.weight": "3.safetensors",
+    "layers.14.linear_attn.in_proj_z.weight": "3.safetensors",
+    "layers.14.linear_attn.in_proj_b.weight": "3.safetensors",
+    "layers.14.linear_attn.in_proj_a.weight": "3.safetensors",
+    "layers.14.mlp.gate_proj.weight": "3.safetensors",
+    "layers.14.mlp.up_proj.weight": "3.safetensors",
+    "layers.14.mlp.down_proj.weight": "4.safetensors",
+    "layers.14.input_layernorm.weight": "4.safetensors",
+    "layers.14.post_attention_layernorm.weight": "4.safetensors",
+    "layers.15.self_attn.q_proj.weight": "4.safetensors",
+    "layers.15.self_attn.k_proj.weight": "4.safetensors",
+    "layers.15.self_attn.v_proj.weight": "4.safetensors",
+    "layers.15.self_attn.o_proj.weight": "4.safetensors",
+    "layers.15.self_attn.q_norm.weight": "4.safetensors",
+    "layers.15.self_attn.k_norm.weight": "4.safetensors",
+    "layers.15.mlp.gate_proj.weight": "4.safetensors",
+    "layers.15.mlp.up_proj.weight": "4.safetensors",
+    "layers.15.mlp.down_proj.weight": "4.safetensors",
+    "layers.15.input_layernorm.weight": "4.safetensors",
+    "layers.15.post_attention_layernorm.weight": "4.safetensors",
+    "layers.16.linear_attn.conv1d.weight": "4.safetensors",
+    "layers.16.linear_attn.dt_bias": "4.safetensors",
+    "layers.16.linear_attn.A_log": "4.safetensors",
+    "layers.16.linear_attn.norm.weight": "4.safetensors",
+    "layers.16.linear_attn.out_proj.weight": "4.safetensors",
+    "layers.16.linear_attn.in_proj_qkv.weight": "4.safetensors",
+    "layers.16.linear_attn.in_proj_z.weight": "4.safetensors",
+    "layers.16.linear_attn.in_proj_b.weight": "4.safetensors",
+    "layers.16.linear_attn.in_proj_a.weight": "4.safetensors",
+    "layers.16.mlp.gate_proj.weight": "4.safetensors",
+    "layers.16.mlp.up_proj.weight": "4.safetensors",
+    "layers.16.mlp.down_proj.weight": "4.safetensors",
+    "layers.16.input_layernorm.weight": "4.safetensors",
+    "layers.16.post_attention_layernorm.weight": "4.safetensors",
+    "layers.17.linear_attn.conv1d.weight": "4.safetensors",
+    "layers.17.linear_attn.dt_bias": "4.safetensors",
+    "layers.17.linear_attn.A_log": "4.safetensors",
+    "layers.17.linear_attn.norm.weight": "4.safetensors",
+    "layers.17.linear_attn.out_proj.weight": "4.safetensors",
+    "layers.17.linear_attn.in_proj_qkv.weight": "4.safetensors",
+    "layers.17.linear_attn.in_proj_z.weight": "4.safetensors",
+    "layers.17.linear_attn.in_proj_b.weight": "4.safetensors",
+    "layers.17.linear_attn.in_proj_a.weight": "4.safetensors",
+    "layers.17.mlp.gate_proj.weight": "4.safetensors",
+    "layers.17.mlp.up_proj.weight": "4.safetensors",
+    "layers.17.mlp.down_proj.weight": "4.safetensors",
+    "layers.17.input_layernorm.weight": "4.safetensors",
+    "layers.17.post_attention_layernorm.weight": "4.safetensors",
+    "layers.18.linear_attn.conv1d.weight": "4.safetensors",
+    "layers.18.linear_attn.dt_bias": "4.safetensors",
+    "layers.18.linear_attn.A_log": "4.safetensors",
+    "layers.18.linear_attn.norm.weight": "4.safetensors",
+    "layers.18.linear_attn.out_proj.weight": "4.safetensors",
+    "layers.18.linear_attn.in_proj_qkv.weight": "4.safetensors",
+    "layers.18.linear_attn.in_proj_z.weight": "4.safetensors",
+    "layers.18.linear_attn.in_proj_b.weight": "4.safetensors",
+    "layers.18.linear_attn.in_proj_a.weight": "4.safetensors",
+    "layers.18.mlp.gate_proj.weight": "4.safetensors",
+    "layers.18.mlp.up_proj.weight": "4.safetensors",
+    "layers.18.mlp.down_proj.weight": "4.safetensors",
+    "layers.18.input_layernorm.weight": "4.safetensors",
+    "layers.18.post_attention_layernorm.weight": "4.safetensors",
+    "layers.19.self_attn.q_proj.weight": "4.safetensors",
+    "layers.19.self_attn.k_proj.weight": "4.safetensors",
+    "layers.19.self_attn.v_proj.weight": "4.safetensors",
+    "layers.19.self_attn.o_proj.weight": "4.safetensors",
+    "layers.19.self_attn.q_norm.weight": "4.safetensors",
+    "layers.19.self_attn.k_norm.weight": "4.safetensors",
+    "layers.19.mlp.gate_proj.weight": "4.safetensors",
+    "layers.19.mlp.up_proj.weight": "5.safetensors",
+    "layers.19.mlp.down_proj.weight": "5.safetensors",
+    "layers.19.input_layernorm.weight": "5.safetensors",
+    "layers.19.post_attention_layernorm.weight": "5.safetensors",
+    "layers.20.linear_attn.conv1d.weight": "5.safetensors",
+    "layers.20.linear_attn.dt_bias": "5.safetensors",
+    "layers.20.linear_attn.A_log": "5.safetensors",
+    "layers.20.linear_attn.norm.weight": "5.safetensors",
+    "layers.20.linear_attn.out_proj.weight": "5.safetensors",
+    "layers.20.linear_attn.in_proj_qkv.weight": "5.safetensors",
+    "layers.20.linear_attn.in_proj_z.weight": "5.safetensors",
+    "layers.20.linear_attn.in_proj_b.weight": "5.safetensors",
+    "layers.20.linear_attn.in_proj_a.weight": "5.safetensors",
+    "layers.20.mlp.gate_proj.weight": "5.safetensors",
+    "layers.20.mlp.up_proj.weight": "5.safetensors",
+    "layers.20.mlp.down_proj.weight": "5.safetensors",
+    "layers.20.input_layernorm.weight": "5.safetensors",
+    "layers.20.post_attention_layernorm.weight": "5.safetensors",
+    "layers.21.linear_attn.conv1d.weight": "5.safetensors",
+    "layers.21.linear_attn.dt_bias": "5.safetensors",
+    "layers.21.linear_attn.A_log": "5.safetensors",
+    "layers.21.linear_attn.norm.weight": "5.safetensors",
+    "layers.21.linear_attn.out_proj.weight": "5.safetensors",
+    "layers.21.linear_attn.in_proj_qkv.weight": "5.safetensors",
+    "layers.21.linear_attn.in_proj_z.weight": "5.safetensors",
+    "layers.21.linear_attn.in_proj_b.weight": "5.safetensors",
+    "layers.21.linear_attn.in_proj_a.weight": "5.safetensors",
+    "layers.21.mlp.gate_proj.weight": "5.safetensors",
+    "layers.21.mlp.up_proj.weight": "5.safetensors",
+    "layers.21.mlp.down_proj.weight": "5.safetensors",
+    "layers.21.input_layernorm.weight": "5.safetensors",
+    "layers.21.post_attention_layernorm.weight": "5.safetensors",
+    "layers.22.linear_attn.conv1d.weight": "5.safetensors",
+    "layers.22.linear_attn.dt_bias": "5.safetensors",
+    "layers.22.linear_attn.A_log": "5.safetensors",
+    "layers.22.linear_attn.norm.weight": "5.safetensors",
+    "layers.22.linear_attn.out_proj.weight": "5.safetensors",
+    "layers.22.linear_attn.in_proj_qkv.weight": "5.safetensors",
+    "layers.22.linear_attn.in_proj_z.weight": "5.safetensors",
+    "layers.22.linear_attn.in_proj_b.weight": "5.safetensors",
+    "layers.22.linear_attn.in_proj_a.weight": "5.safetensors",
+    "layers.22.mlp.gate_proj.weight": "5.safetensors",
+    "layers.22.mlp.up_proj.weight": "5.safetensors",
+    "layers.22.mlp.down_proj.weight": "5.safetensors",
+    "layers.22.input_layernorm.weight": "5.safetensors",
+    "layers.22.post_attention_layernorm.weight": "5.safetensors",
+    "layers.23.self_attn.q_proj.weight": "5.safetensors",
+    "layers.23.self_attn.k_proj.weight": "5.safetensors",
+    "layers.23.self_attn.v_proj.weight": "5.safetensors",
+    "layers.23.self_attn.o_proj.weight": "5.safetensors",
+    "layers.23.self_attn.q_norm.weight": "5.safetensors",
+    "layers.23.self_attn.k_norm.weight": "5.safetensors",
+    "layers.23.mlp.gate_proj.weight": "5.safetensors",
+    "layers.23.mlp.up_proj.weight": "5.safetensors",
+    "layers.23.mlp.down_proj.weight": "5.safetensors",
+    "layers.23.input_layernorm.weight": "5.safetensors",
+    "layers.23.post_attention_layernorm.weight": "5.safetensors",
+    "layers.24.linear_attn.conv1d.weight": "5.safetensors",
+    "layers.24.linear_attn.dt_bias": "5.safetensors",
+    "layers.24.linear_attn.A_log": "5.safetensors",
+    "layers.24.linear_attn.norm.weight": "5.safetensors",
+    "layers.24.linear_attn.out_proj.weight": "5.safetensors",
+    "layers.24.linear_attn.in_proj_qkv.weight": "5.safetensors",
+    "layers.24.linear_attn.in_proj_z.weight": "5.safetensors",
+    "layers.24.linear_attn.in_proj_b.weight": "5.safetensors",
+    "layers.24.linear_attn.in_proj_a.weight": "5.safetensors",
+    "layers.24.mlp.gate_proj.weight": "6.safetensors",
+    "layers.24.mlp.up_proj.weight": "6.safetensors",
+    "layers.24.mlp.down_proj.weight": "6.safetensors",
+    "layers.24.input_layernorm.weight": "6.safetensors",
+    "layers.24.post_attention_layernorm.weight": "6.safetensors",
+    "layers.25.linear_attn.conv1d.weight": "6.safetensors",
+    "layers.25.linear_attn.dt_bias": "6.safetensors",
+    "layers.25.linear_attn.A_log": "6.safetensors",
+    "layers.25.linear_attn.norm.weight": "6.safetensors",
+    "layers.25.linear_attn.out_proj.weight": "6.safetensors",
+    "layers.25.linear_attn.in_proj_qkv.weight": "6.safetensors",
+    "layers.25.linear_attn.in_proj_z.weight": "6.safetensors",
+    "layers.25.linear_attn.in_proj_b.weight": "6.safetensors",
+    "layers.25.linear_attn.in_proj_a.weight": "6.safetensors",
+    "layers.25.mlp.gate_proj.weight": "6.safetensors",
+    "layers.25.mlp.up_proj.weight": "6.safetensors",
+    "layers.25.mlp.down_proj.weight": "6.safetensors",
+    "layers.25.input_layernorm.weight": "6.safetensors",
+    "layers.25.post_attention_layernorm.weight": "6.safetensors",
+    "layers.26.linear_attn.conv1d.weight": "6.safetensors",
+    "layers.26.linear_attn.dt_bias": "6.safetensors",
+    "layers.26.linear_attn.A_log": "6.safetensors",
+    "layers.26.linear_attn.norm.weight": "6.safetensors",
+    "layers.26.linear_attn.out_proj.weight": "6.safetensors",
+    "layers.26.linear_attn.in_proj_qkv.weight": "6.safetensors",
+    "layers.26.linear_attn.in_proj_z.weight": "6.safetensors",
+    "layers.26.linear_attn.in_proj_b.weight": "6.safetensors",
+    "layers.26.linear_attn.in_proj_a.weight": "6.safetensors",
+    "layers.26.mlp.gate_proj.weight": "6.safetensors",
+    "layers.26.mlp.up_proj.weight": "6.safetensors",
+    "layers.26.mlp.down_proj.weight": "6.safetensors",
+    "layers.26.input_layernorm.weight": "6.safetensors",
+    "layers.26.post_attention_layernorm.weight": "6.safetensors",
+    "layers.27.self_attn.q_proj.weight": "6.safetensors",
+    "layers.27.self_attn.k_proj.weight": "6.safetensors",
+    "layers.27.self_attn.v_proj.weight": "6.safetensors",
+    "layers.27.self_attn.o_proj.weight": "6.safetensors",
+    "layers.27.self_attn.q_norm.weight": "6.safetensors",
+    "layers.27.self_attn.k_norm.weight": "6.safetensors",
+    "layers.27.mlp.gate_proj.weight": "6.safetensors",
+    "layers.27.mlp.up_proj.weight": "6.safetensors",
+    "layers.27.mlp.down_proj.weight": "6.safetensors",
+    "layers.27.input_layernorm.weight": "6.safetensors",
+    "layers.27.post_attention_layernorm.weight": "6.safetensors",
+    "layers.28.linear_attn.conv1d.weight": "6.safetensors",
+    "layers.28.linear_attn.dt_bias": "6.safetensors",
+    "layers.28.linear_attn.A_log": "6.safetensors",
+    "layers.28.linear_attn.norm.weight": "6.safetensors",
+    "layers.28.linear_attn.out_proj.weight": "6.safetensors",
+    "layers.28.linear_attn.in_proj_qkv.weight": "6.safetensors",
+    "layers.28.linear_attn.in_proj_z.weight": "6.safetensors",
+    "layers.28.linear_attn.in_proj_b.weight": "6.safetensors",
+    "layers.28.linear_attn.in_proj_a.weight": "6.safetensors",
+    "layers.28.mlp.gate_proj.weight": "6.safetensors",
+    "layers.28.mlp.up_proj.weight": "6.safetensors",
+    "layers.28.mlp.down_proj.weight": "6.safetensors",
+    "layers.28.input_layernorm.weight": "6.safetensors",
+    "layers.28.post_attention_layernorm.weight": "6.safetensors",
+    "layers.29.linear_attn.conv1d.weight": "6.safetensors",
+    "layers.29.linear_attn.dt_bias": "6.safetensors",
+    "layers.29.linear_attn.A_log": "6.safetensors",
+    "layers.29.linear_attn.norm.weight": "6.safetensors",
+    "layers.29.linear_attn.out_proj.weight": "6.safetensors",
+    "layers.29.linear_attn.in_proj_qkv.weight": "6.safetensors",
+    "layers.29.linear_attn.in_proj_z.weight": "7.safetensors",
+    "layers.29.linear_attn.in_proj_b.weight": "7.safetensors",
+    "layers.29.linear_attn.in_proj_a.weight": "7.safetensors",
+    "layers.29.mlp.gate_proj.weight": "7.safetensors",
+    "layers.29.mlp.up_proj.weight": "7.safetensors",
+    "layers.29.mlp.down_proj.weight": "7.safetensors",
+    "layers.29.input_layernorm.weight": "7.safetensors",
+    "layers.29.post_attention_layernorm.weight": "7.safetensors",
+    "layers.30.linear_attn.conv1d.weight": "7.safetensors",
+    "layers.30.linear_attn.dt_bias": "7.safetensors",
+    "layers.30.linear_attn.A_log": "7.safetensors",
+    "layers.30.linear_attn.norm.weight": "7.safetensors",
+    "layers.30.linear_attn.out_proj.weight": "7.safetensors",
+    "layers.30.linear_attn.in_proj_qkv.weight": "7.safetensors",
+    "layers.30.linear_attn.in_proj_z.weight": "7.safetensors",
+    "layers.30.linear_attn.in_proj_b.weight": "7.safetensors",
+    "layers.30.linear_attn.in_proj_a.weight": "7.safetensors",
+    "layers.30.mlp.gate_proj.weight": "7.safetensors",
+    "layers.30.mlp.up_proj.weight": "7.safetensors",
+    "layers.30.mlp.down_proj.weight": "7.safetensors",
+    "layers.30.input_layernorm.weight": "7.safetensors",
+    "layers.30.post_attention_layernorm.weight": "7.safetensors",
+    "layers.31.self_attn.q_proj.weight": "7.safetensors",
+    "layers.31.self_attn.k_proj.weight": "7.safetensors",
+    "layers.31.self_attn.v_proj.weight": "7.safetensors",
+    "layers.31.self_attn.o_proj.weight": "7.safetensors",
+    "layers.31.self_attn.q_norm.weight": "7.safetensors",
+    "layers.31.self_attn.k_norm.weight": "7.safetensors",
+    "layers.31.mlp.gate_proj.weight": "7.safetensors",
+    "layers.31.mlp.up_proj.weight": "7.safetensors",
+    "layers.31.mlp.down_proj.weight": "7.safetensors",
+    "layers.31.input_layernorm.weight": "7.safetensors",
+    "layers.31.post_attention_layernorm.weight": "7.safetensors",
+    "norm.weight": "7.safetensors"
+  }
+}

bf16/tokenizer/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

bf16/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

bf16/tokenizer/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

bf16/transformer/0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff269e76dc5da9583ba8642872745db0ec559295253af5a8d5546b5e1851e2eb
+size 2047396961

bf16/transformer/1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1e65cda935a9587726350c25b086cc85344788a7a3b48c1bf51385034885cc
+size 2139219437

bf16/transformer/2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961108991d7cf38e4f5800ba2614e7420c65c2c15073a9943594993e6b1a88dd
+size 2145524407

bf16/transformer/3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9d213a41bec6f9952dd53fa11f7608a8b8f4b8b2888d2f71b902718914a230
+size 2057430498

bf16/transformer/4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d255a1280146992dfc749bf4665ab8c664f4382ea689b8d6b522be338f616de9
+size 1775092749

bf16/transformer/model.safetensors.index.json

@@ -0,0 +1,470 @@
+{
+  "metadata": {
+    "quantization_level": "None",
+    "mflux_version": "0.24.0"
+  },
+  "weight_map": {
+    "video_embedder.weight": "0.safetensors",
+    "video_embedder.bias": "0.safetensors",
+    "text_embedder.proj.weight": "0.safetensors",
+    "text_embedder.proj.bias": "0.safetensors",
+    "text_embedder.blocks.0.norm1.weight": "0.safetensors",
+    "text_embedder.blocks.0.norm2.weight": "0.safetensors",
+    "text_embedder.blocks.0.q_norm.weight": "0.safetensors",
+    "text_embedder.blocks.0.k_norm.weight": "0.safetensors",
+    "text_embedder.blocks.0.qkv.weight": "0.safetensors",
+    "text_embedder.blocks.0.qkv.bias": "0.safetensors",
+    "text_embedder.blocks.0.proj.weight": "0.safetensors",
+    "text_embedder.blocks.0.proj.bias": "0.safetensors",
+    "text_embedder.blocks.0.ffn_gate.weight": "0.safetensors",
+    "text_embedder.blocks.0.ffn_gate.bias": "0.safetensors",
+    "text_embedder.blocks.0.ffn_up.weight": "0.safetensors",
+    "text_embedder.blocks.0.ffn_up.bias": "0.safetensors",
+    "text_embedder.blocks.0.ffn_down.weight": "0.safetensors",
+    "text_embedder.blocks.0.ffn_down.bias": "0.safetensors",
+    "text_embedder.blocks.1.norm1.weight": "0.safetensors",
+    "text_embedder.blocks.1.norm2.weight": "0.safetensors",
+    "text_embedder.blocks.1.q_norm.weight": "0.safetensors",
+    "text_embedder.blocks.1.k_norm.weight": "0.safetensors",
+    "text_embedder.blocks.1.qkv.weight": "0.safetensors",
+    "text_embedder.blocks.1.qkv.bias": "0.safetensors",
+    "text_embedder.blocks.1.proj.weight": "0.safetensors",
+    "text_embedder.blocks.1.proj.bias": "0.safetensors",
+    "text_embedder.blocks.1.ffn_gate.weight": "0.safetensors",
+    "text_embedder.blocks.1.ffn_gate.bias": "0.safetensors",
+    "text_embedder.blocks.1.ffn_up.weight": "0.safetensors",
+    "text_embedder.blocks.1.ffn_up.bias": "0.safetensors",
+    "text_embedder.blocks.1.ffn_down.weight": "0.safetensors",
+    "text_embedder.blocks.1.ffn_down.bias": "0.safetensors",
+    "time_embedding.0.weight": "0.safetensors",
+    "time_embedding.0.bias": "0.safetensors",
+    "time_embedding.2.weight": "0.safetensors",
+    "time_embedding.2.bias": "0.safetensors",
+    "shared_block_modulation.weight": "0.safetensors",
+    "shared_block_modulation.bias": "0.safetensors",
+    "layers.0.norm1.weight": "0.safetensors",
+    "layers.0.norm2.weight": "0.safetensors",
+    "layers.0.q_norm.weight": "0.safetensors",
+    "layers.0.k_norm.weight": "0.safetensors",
+    "layers.0.proj.q.weight": "0.safetensors",
+    "layers.0.proj.k.weight": "0.safetensors",
+    "layers.0.proj.v.weight": "0.safetensors",
+    "layers.0.proj.o.weight": "0.safetensors",
+    "layers.0.proj.ffn_up_gate.weight": "0.safetensors",
+    "layers.0.proj.ffn_down.weight": "0.safetensors",
+    "layers.1.norm1.weight": "0.safetensors",
+    "layers.1.norm2.weight": "0.safetensors",
+    "layers.1.q_norm.weight": "0.safetensors",
+    "layers.1.k_norm.weight": "0.safetensors",
+    "layers.1.proj.q.weight": "0.safetensors",
+    "layers.1.proj.k.weight": "0.safetensors",
+    "layers.1.proj.v.weight": "0.safetensors",
+    "layers.1.proj.o.weight": "0.safetensors",
+    "layers.1.proj.ffn_up_gate.weight": "0.safetensors",
+    "layers.1.proj.ffn_down.weight": "0.safetensors",
+    "layers.2.norm1.weight": "0.safetensors",
+    "layers.2.norm2.weight": "0.safetensors",
+    "layers.2.q_norm.weight": "0.safetensors",
+    "layers.2.k_norm.weight": "0.safetensors",
+    "layers.2.proj.q.weight": "0.safetensors",
+    "layers.2.proj.k.weight": "0.safetensors",
+    "layers.2.proj.v.weight": "0.safetensors",
+    "layers.2.proj.o.weight": "0.safetensors",
+    "layers.2.proj.ffn_up_gate.weight": "0.safetensors",
+    "layers.2.proj.ffn_down.weight": "0.safetensors",
+    "layers.3.norm1.weight": "0.safetensors",
+    "layers.3.norm2.weight": "0.safetensors",
+    "layers.3.q_norm.weight": "0.safetensors",
+    "layers.3.k_norm.weight": "0.safetensors",
+    "layers.3.proj.q.weight": "0.safetensors",
+    "layers.3.proj.k.weight": "0.safetensors",
+    "layers.3.proj.v.weight": "0.safetensors",
+    "layers.3.proj.o.weight": "0.safetensors",
+    "layers.3.proj.ffn_up_gate.weight": "0.safetensors",
+    "layers.3.proj.ffn_down.weight": "0.safetensors",
+    "layers.4.norm1.weight": "0.safetensors",
+    "layers.4.norm2.weight": "0.safetensors",
+    "layers.4.q_norm.weight": "0.safetensors",
+    "layers.4.k_norm.weight": "0.safetensors",
+    "layers.4.proj.q.weight": "0.safetensors",
+    "layers.4.proj.k.weight": "0.safetensors",
+    "layers.4.proj.v.weight": "0.safetensors",
+    "layers.4.proj.o.weight": "0.safetensors",
+    "layers.4.proj.ffn_up_gate.weight": "0.safetensors",
+    "layers.4.proj.ffn_down.weight": "0.safetensors",
+    "layers.5.norm1.weight": "0.safetensors",
+    "layers.5.norm2.weight": "0.safetensors",
+    "layers.5.q_norm.weight": "0.safetensors",
+    "layers.5.k_norm.weight": "0.safetensors",
+    "layers.5.proj.q.weight": "0.safetensors",
+    "layers.5.proj.k.weight": "0.safetensors",
+    "layers.5.proj.v.weight": "0.safetensors",
+    "layers.5.proj.o.weight": "0.safetensors",
+    "layers.5.proj.ffn_up_gate.weight": "0.safetensors",
+    "layers.5.proj.ffn_down.weight": "0.safetensors",
+    "layers.6.norm1.weight": "0.safetensors",
+    "layers.6.norm2.weight": "0.safetensors",
+    "layers.6.q_norm.weight": "0.safetensors",
+    "layers.6.k_norm.weight": "0.safetensors",
+    "layers.6.proj.q.weight": "0.safetensors",
+    "layers.6.proj.k.weight": "0.safetensors",
+    "layers.6.proj.v.weight": "0.safetensors",
+    "layers.6.proj.o.weight": "0.safetensors",
+    "layers.6.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.6.proj.ffn_down.weight": "1.safetensors",
+    "layers.7.norm1.weight": "1.safetensors",
+    "layers.7.norm2.weight": "1.safetensors",
+    "layers.7.q_norm.weight": "1.safetensors",
+    "layers.7.k_norm.weight": "1.safetensors",
+    "layers.7.proj.q.weight": "1.safetensors",
+    "layers.7.proj.k.weight": "1.safetensors",
+    "layers.7.proj.v.weight": "1.safetensors",
+    "layers.7.proj.o.weight": "1.safetensors",
+    "layers.7.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.7.proj.ffn_down.weight": "1.safetensors",
+    "layers.8.norm1.weight": "1.safetensors",
+    "layers.8.norm2.weight": "1.safetensors",
+    "layers.8.q_norm.weight": "1.safetensors",
+    "layers.8.k_norm.weight": "1.safetensors",
+    "layers.8.proj.q.weight": "1.safetensors",
+    "layers.8.proj.k.weight": "1.safetensors",
+    "layers.8.proj.v.weight": "1.safetensors",
+    "layers.8.proj.o.weight": "1.safetensors",
+    "layers.8.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.8.proj.ffn_down.weight": "1.safetensors",
+    "layers.9.norm1.weight": "1.safetensors",
+    "layers.9.norm2.weight": "1.safetensors",
+    "layers.9.q_norm.weight": "1.safetensors",
+    "layers.9.k_norm.weight": "1.safetensors",
+    "layers.9.proj.q.weight": "1.safetensors",
+    "layers.9.proj.k.weight": "1.safetensors",
+    "layers.9.proj.v.weight": "1.safetensors",
+    "layers.9.proj.o.weight": "1.safetensors",
+    "layers.9.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.9.proj.ffn_down.weight": "1.safetensors",
+    "layers.10.norm1.weight": "1.safetensors",
+    "layers.10.norm2.weight": "1.safetensors",
+    "layers.10.q_norm.weight": "1.safetensors",
+    "layers.10.k_norm.weight": "1.safetensors",
+    "layers.10.proj.q.weight": "1.safetensors",
+    "layers.10.proj.k.weight": "1.safetensors",
+    "layers.10.proj.v.weight": "1.safetensors",
+    "layers.10.proj.o.weight": "1.safetensors",
+    "layers.10.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.10.proj.ffn_down.weight": "1.safetensors",
+    "layers.11.norm1.weight": "1.safetensors",
+    "layers.11.norm2.weight": "1.safetensors",
+    "layers.11.q_norm.weight": "1.safetensors",
+    "layers.11.k_norm.weight": "1.safetensors",
+    "layers.11.proj.q.weight": "1.safetensors",
+    "layers.11.proj.k.weight": "1.safetensors",
+    "layers.11.proj.v.weight": "1.safetensors",
+    "layers.11.proj.o.weight": "1.safetensors",
+    "layers.11.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.11.proj.ffn_down.weight": "1.safetensors",
+    "layers.12.norm1.weight": "1.safetensors",
+    "layers.12.norm2.weight": "1.safetensors",
+    "layers.12.q_norm.weight": "1.safetensors",
+    "layers.12.k_norm.weight": "1.safetensors",
+    "layers.12.proj.q.weight": "1.safetensors",
+    "layers.12.proj.k.weight": "1.safetensors",
+    "layers.12.proj.v.weight": "1.safetensors",
+    "layers.12.proj.o.weight": "1.safetensors",
+    "layers.12.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.12.proj.ffn_down.weight": "1.safetensors",
+    "layers.13.norm1.weight": "1.safetensors",
+    "layers.13.norm2.weight": "1.safetensors",
+    "layers.13.q_norm.weight": "1.safetensors",
+    "layers.13.k_norm.weight": "1.safetensors",
+    "layers.13.proj.q.weight": "1.safetensors",
+    "layers.13.proj.k.weight": "1.safetensors",
+    "layers.13.proj.v.weight": "1.safetensors",
+    "layers.13.proj.o.weight": "1.safetensors",
+    "layers.13.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.13.proj.ffn_down.weight": "1.safetensors",
+    "layers.14.norm1.weight": "1.safetensors",
+    "layers.14.norm2.weight": "1.safetensors",
+    "layers.14.q_norm.weight": "1.safetensors",
+    "layers.14.k_norm.weight": "1.safetensors",
+    "layers.14.proj.q.weight": "1.safetensors",
+    "layers.14.proj.k.weight": "1.safetensors",
+    "layers.14.proj.v.weight": "1.safetensors",
+    "layers.14.proj.o.weight": "1.safetensors",
+    "layers.14.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.14.proj.ffn_down.weight": "1.safetensors",
+    "layers.15.norm1.weight": "1.safetensors",
+    "layers.15.norm2.weight": "1.safetensors",
+    "layers.15.q_norm.weight": "1.safetensors",
+    "layers.15.k_norm.weight": "1.safetensors",
+    "layers.15.proj.q.weight": "1.safetensors",
+    "layers.15.proj.k.weight": "1.safetensors",
+    "layers.15.proj.v.weight": "1.safetensors",
+    "layers.15.proj.o.weight": "1.safetensors",
+    "layers.15.proj.ffn_up_gate.weight": "1.safetensors",
+    "layers.15.proj.ffn_down.weight": "2.safetensors",
+    "layers.16.norm1.weight": "2.safetensors",
+    "layers.16.norm2.weight": "2.safetensors",
+    "layers.16.q_norm.weight": "2.safetensors",
+    "layers.16.k_norm.weight": "2.safetensors",
+    "layers.16.proj.q.weight": "2.safetensors",
+    "layers.16.proj.k.weight": "2.safetensors",
+    "layers.16.proj.v.weight": "2.safetensors",
+    "layers.16.proj.o.weight": "2.safetensors",
+    "layers.16.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.16.proj.ffn_down.weight": "2.safetensors",
+    "layers.17.norm1.weight": "2.safetensors",
+    "layers.17.norm2.weight": "2.safetensors",
+    "layers.17.q_norm.weight": "2.safetensors",
+    "layers.17.k_norm.weight": "2.safetensors",
+    "layers.17.proj.q.weight": "2.safetensors",
+    "layers.17.proj.k.weight": "2.safetensors",
+    "layers.17.proj.v.weight": "2.safetensors",
+    "layers.17.proj.o.weight": "2.safetensors",
+    "layers.17.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.17.proj.ffn_down.weight": "2.safetensors",
+    "layers.18.norm1.weight": "2.safetensors",
+    "layers.18.norm2.weight": "2.safetensors",
+    "layers.18.q_norm.weight": "2.safetensors",
+    "layers.18.k_norm.weight": "2.safetensors",
+    "layers.18.proj.q.weight": "2.safetensors",
+    "layers.18.proj.k.weight": "2.safetensors",
+    "layers.18.proj.v.weight": "2.safetensors",
+    "layers.18.proj.o.weight": "2.safetensors",
+    "layers.18.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.18.proj.ffn_down.weight": "2.safetensors",
+    "layers.19.norm1.weight": "2.safetensors",
+    "layers.19.norm2.weight": "2.safetensors",
+    "layers.19.q_norm.weight": "2.safetensors",
+    "layers.19.k_norm.weight": "2.safetensors",
+    "layers.19.proj.q.weight": "2.safetensors",
+    "layers.19.proj.k.weight": "2.safetensors",
+    "layers.19.proj.v.weight": "2.safetensors",
+    "layers.19.proj.o.weight": "2.safetensors",
+    "layers.19.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.19.proj.ffn_down.weight": "2.safetensors",
+    "layers.20.norm1.weight": "2.safetensors",
+    "layers.20.norm2.weight": "2.safetensors",
+    "layers.20.q_norm.weight": "2.safetensors",
+    "layers.20.k_norm.weight": "2.safetensors",
+    "layers.20.proj.q.weight": "2.safetensors",
+    "layers.20.proj.k.weight": "2.safetensors",
+    "layers.20.proj.v.weight": "2.safetensors",
+    "layers.20.proj.o.weight": "2.safetensors",
+    "layers.20.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.20.proj.ffn_down.weight": "2.safetensors",
+    "layers.21.norm1.weight": "2.safetensors",
+    "layers.21.norm2.weight": "2.safetensors",
+    "layers.21.q_norm.weight": "2.safetensors",
+    "layers.21.k_norm.weight": "2.safetensors",
+    "layers.21.proj.q.weight": "2.safetensors",
+    "layers.21.proj.k.weight": "2.safetensors",
+    "layers.21.proj.v.weight": "2.safetensors",
+    "layers.21.proj.o.weight": "2.safetensors",
+    "layers.21.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.21.proj.ffn_down.weight": "2.safetensors",
+    "layers.22.norm1.weight": "2.safetensors",
+    "layers.22.norm2.weight": "2.safetensors",
+    "layers.22.q_norm.weight": "2.safetensors",
+    "layers.22.k_norm.weight": "2.safetensors",
+    "layers.22.proj.q.weight": "2.safetensors",
+    "layers.22.proj.k.weight": "2.safetensors",
+    "layers.22.proj.v.weight": "2.safetensors",
+    "layers.22.proj.o.weight": "2.safetensors",
+    "layers.22.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.22.proj.ffn_down.weight": "2.safetensors",
+    "layers.23.norm1.weight": "2.safetensors",
+    "layers.23.norm2.weight": "2.safetensors",
+    "layers.23.q_norm.weight": "2.safetensors",
+    "layers.23.k_norm.weight": "2.safetensors",
+    "layers.23.proj.q.weight": "2.safetensors",
+    "layers.23.proj.k.weight": "2.safetensors",
+    "layers.23.proj.v.weight": "2.safetensors",
+    "layers.23.proj.o.weight": "2.safetensors",
+    "layers.23.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.23.proj.ffn_down.weight": "2.safetensors",
+    "layers.24.norm1.weight": "2.safetensors",
+    "layers.24.norm2.weight": "2.safetensors",
+    "layers.24.q_norm.weight": "2.safetensors",
+    "layers.24.k_norm.weight": "2.safetensors",
+    "layers.24.proj.q.weight": "2.safetensors",
+    "layers.24.proj.k.weight": "2.safetensors",
+    "layers.24.proj.v.weight": "2.safetensors",
+    "layers.24.proj.o.weight": "2.safetensors",
+    "layers.24.proj.ffn_up_gate.weight": "2.safetensors",
+    "layers.24.proj.ffn_down.weight": "2.safetensors",
+    "layers.25.norm1.weight": "2.safetensors",
+    "layers.25.norm2.weight": "2.safetensors",
+    "layers.25.q_norm.weight": "2.safetensors",
+    "layers.25.k_norm.weight": "2.safetensors",
+    "layers.25.proj.q.weight": "2.safetensors",
+    "layers.25.proj.k.weight": "2.safetensors",
+    "layers.25.proj.v.weight": "2.safetensors",
+    "layers.25.proj.o.weight": "3.safetensors",
+    "layers.25.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.25.proj.ffn_down.weight": "3.safetensors",
+    "layers.26.norm1.weight": "3.safetensors",
+    "layers.26.norm2.weight": "3.safetensors",
+    "layers.26.q_norm.weight": "3.safetensors",
+    "layers.26.k_norm.weight": "3.safetensors",
+    "layers.26.proj.q.weight": "3.safetensors",
+    "layers.26.proj.k.weight": "3.safetensors",
+    "layers.26.proj.v.weight": "3.safetensors",
+    "layers.26.proj.o.weight": "3.safetensors",
+    "layers.26.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.26.proj.ffn_down.weight": "3.safetensors",
+    "layers.27.norm1.weight": "3.safetensors",
+    "layers.27.norm2.weight": "3.safetensors",
+    "layers.27.q_norm.weight": "3.safetensors",
+    "layers.27.k_norm.weight": "3.safetensors",
+    "layers.27.proj.q.weight": "3.safetensors",
+    "layers.27.proj.k.weight": "3.safetensors",
+    "layers.27.proj.v.weight": "3.safetensors",
+    "layers.27.proj.o.weight": "3.safetensors",
+    "layers.27.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.27.proj.ffn_down.weight": "3.safetensors",
+    "layers.28.norm1.weight": "3.safetensors",
+    "layers.28.norm2.weight": "3.safetensors",
+    "layers.28.q_norm.weight": "3.safetensors",
+    "layers.28.k_norm.weight": "3.safetensors",
+    "layers.28.proj.q.weight": "3.safetensors",
+    "layers.28.proj.k.weight": "3.safetensors",
+    "layers.28.proj.v.weight": "3.safetensors",
+    "layers.28.proj.o.weight": "3.safetensors",
+    "layers.28.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.28.proj.ffn_down.weight": "3.safetensors",
+    "layers.29.norm1.weight": "3.safetensors",
+    "layers.29.norm2.weight": "3.safetensors",
+    "layers.29.q_norm.weight": "3.safetensors",
+    "layers.29.k_norm.weight": "3.safetensors",
+    "layers.29.proj.q.weight": "3.safetensors",
+    "layers.29.proj.k.weight": "3.safetensors",
+    "layers.29.proj.v.weight": "3.safetensors",
+    "layers.29.proj.o.weight": "3.safetensors",
+    "layers.29.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.29.proj.ffn_down.weight": "3.safetensors",
+    "layers.30.norm1.weight": "3.safetensors",
+    "layers.30.norm2.weight": "3.safetensors",
+    "layers.30.q_norm.weight": "3.safetensors",
+    "layers.30.k_norm.weight": "3.safetensors",
+    "layers.30.proj.q.weight": "3.safetensors",
+    "layers.30.proj.k.weight": "3.safetensors",
+    "layers.30.proj.v.weight": "3.safetensors",
+    "layers.30.proj.o.weight": "3.safetensors",
+    "layers.30.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.30.proj.ffn_down.weight": "3.safetensors",
+    "layers.31.norm1.weight": "3.safetensors",
+    "layers.31.norm2.weight": "3.safetensors",
+    "layers.31.q_norm.weight": "3.safetensors",
+    "layers.31.k_norm.weight": "3.safetensors",
+    "layers.31.proj.q.weight": "3.safetensors",
+    "layers.31.proj.k.weight": "3.safetensors",
+    "layers.31.proj.v.weight": "3.safetensors",
+    "layers.31.proj.o.weight": "3.safetensors",
+    "layers.31.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.31.proj.ffn_down.weight": "3.safetensors",
+    "layers.32.norm1.weight": "3.safetensors",
+    "layers.32.norm2.weight": "3.safetensors",
+    "layers.32.q_norm.weight": "3.safetensors",
+    "layers.32.k_norm.weight": "3.safetensors",
+    "layers.32.proj.q.weight": "3.safetensors",
+    "layers.32.proj.k.weight": "3.safetensors",
+    "layers.32.proj.v.weight": "3.safetensors",
+    "layers.32.proj.o.weight": "3.safetensors",
+    "layers.32.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.32.proj.ffn_down.weight": "3.safetensors",
+    "layers.33.norm1.weight": "3.safetensors",
+    "layers.33.norm2.weight": "3.safetensors",
+    "layers.33.q_norm.weight": "3.safetensors",
+    "layers.33.k_norm.weight": "3.safetensors",
+    "layers.33.proj.q.weight": "3.safetensors",
+    "layers.33.proj.k.weight": "3.safetensors",
+    "layers.33.proj.v.weight": "3.safetensors",
+    "layers.33.proj.o.weight": "3.safetensors",
+    "layers.33.proj.ffn_up_gate.weight": "3.safetensors",
+    "layers.33.proj.ffn_down.weight": "3.safetensors",
+    "layers.34.norm1.weight": "3.safetensors",
+    "layers.34.norm2.weight": "3.safetensors",
+    "layers.34.q_norm.weight": "3.safetensors",
+    "layers.34.k_norm.weight": "3.safetensors",
+    "layers.34.proj.q.weight": "3.safetensors",
+    "layers.34.proj.k.weight": "3.safetensors",
+    "layers.34.proj.v.weight": "3.safetensors",
+    "layers.34.proj.o.weight": "3.safetensors",
+    "layers.34.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.34.proj.ffn_down.weight": "4.safetensors",
+    "layers.35.norm1.weight": "4.safetensors",
+    "layers.35.norm2.weight": "4.safetensors",
+    "layers.35.q_norm.weight": "4.safetensors",
+    "layers.35.k_norm.weight": "4.safetensors",
+    "layers.35.proj.q.weight": "4.safetensors",
+    "layers.35.proj.k.weight": "4.safetensors",
+    "layers.35.proj.v.weight": "4.safetensors",
+    "layers.35.proj.o.weight": "4.safetensors",
+    "layers.35.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.35.proj.ffn_down.weight": "4.safetensors",
+    "layers.36.norm1.weight": "4.safetensors",
+    "layers.36.norm2.weight": "4.safetensors",
+    "layers.36.q_norm.weight": "4.safetensors",
+    "layers.36.k_norm.weight": "4.safetensors",
+    "layers.36.proj.q.weight": "4.safetensors",
+    "layers.36.proj.k.weight": "4.safetensors",
+    "layers.36.proj.v.weight": "4.safetensors",
+    "layers.36.proj.o.weight": "4.safetensors",
+    "layers.36.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.36.proj.ffn_down.weight": "4.safetensors",
+    "layers.37.norm1.weight": "4.safetensors",
+    "layers.37.norm2.weight": "4.safetensors",
+    "layers.37.q_norm.weight": "4.safetensors",
+    "layers.37.k_norm.weight": "4.safetensors",
+    "layers.37.proj.q.weight": "4.safetensors",
+    "layers.37.proj.k.weight": "4.safetensors",
+    "layers.37.proj.v.weight": "4.safetensors",
+    "layers.37.proj.o.weight": "4.safetensors",
+    "layers.37.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.37.proj.ffn_down.weight": "4.safetensors",
+    "layers.38.norm1.weight": "4.safetensors",
+    "layers.38.norm2.weight": "4.safetensors",
+    "layers.38.q_norm.weight": "4.safetensors",
+    "layers.38.k_norm.weight": "4.safetensors",
+    "layers.38.proj.q.weight": "4.safetensors",
+    "layers.38.proj.k.weight": "4.safetensors",
+    "layers.38.proj.v.weight": "4.safetensors",
+    "layers.38.proj.o.weight": "4.safetensors",
+    "layers.38.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.38.proj.ffn_down.weight": "4.safetensors",
+    "layers.39.norm1.weight": "4.safetensors",
+    "layers.39.norm2.weight": "4.safetensors",
+    "layers.39.q_norm.weight": "4.safetensors",
+    "layers.39.k_norm.weight": "4.safetensors",
+    "layers.39.proj.q.weight": "4.safetensors",
+    "layers.39.proj.k.weight": "4.safetensors",
+    "layers.39.proj.v.weight": "4.safetensors",
+    "layers.39.proj.o.weight": "4.safetensors",
+    "layers.39.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.39.proj.ffn_down.weight": "4.safetensors",
+    "layers.40.norm1.weight": "4.safetensors",
+    "layers.40.norm2.weight": "4.safetensors",
+    "layers.40.q_norm.weight": "4.safetensors",
+    "layers.40.k_norm.weight": "4.safetensors",
+    "layers.40.proj.q.weight": "4.safetensors",
+    "layers.40.proj.k.weight": "4.safetensors",
+    "layers.40.proj.v.weight": "4.safetensors",
+    "layers.40.proj.o.weight": "4.safetensors",
+    "layers.40.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.40.proj.ffn_down.weight": "4.safetensors",
+    "layers.41.norm1.weight": "4.safetensors",
+    "layers.41.norm2.weight": "4.safetensors",
+    "layers.41.q_norm.weight": "4.safetensors",
+    "layers.41.k_norm.weight": "4.safetensors",
+    "layers.41.proj.q.weight": "4.safetensors",
+    "layers.41.proj.k.weight": "4.safetensors",
+    "layers.41.proj.v.weight": "4.safetensors",
+    "layers.41.proj.o.weight": "4.safetensors",
+    "layers.41.proj.ffn_up_gate.weight": "4.safetensors",
+    "layers.41.proj.ffn_down.weight": "4.safetensors",
+    "final_norm_video.weight": "4.safetensors",
+    "final_linear_video.weight": "4.safetensors",
+    "video_head_modulation.weight": "4.safetensors",
+    "video_head_modulation.bias": "4.safetensors"
+  }
+}

bf16/vae/0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc64e7a50c958974607f534b5ee96f564f46cfd38926f5963359caf3e42f508
+size 124774595

bf16/vae/model.safetensors.index.json

@@ -0,0 +1,258 @@
+{
+  "metadata": {
+    "quantization_level": "None",
+    "mflux_version": "0.24.0"
+  },
+  "weight_map": {
+    "encoder.conv_in.weight": "0.safetensors",
+    "encoder.conv_in.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.0.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.0.resnets.1.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.conv.weight": "0.safetensors",
+    "encoder.down_blocks.0.downsamplers.0.conv.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.1.resnets.1.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.conv.weight": "0.safetensors",
+    "encoder.down_blocks.1.downsamplers.0.conv.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.2.resnets.1.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.conv.weight": "0.safetensors",
+    "encoder.down_blocks.2.downsamplers.0.conv.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.0.conv2.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv1.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.bias": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.weight": "0.safetensors",
+    "encoder.down_blocks.3.resnets.1.conv2.bias": "0.safetensors",
+    "encoder.mid_block.resnets.0.norm1.bias": "0.safetensors",
+    "encoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv1.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv1.bias": "0.safetensors",
+    "encoder.mid_block.resnets.0.norm2.bias": "0.safetensors",
+    "encoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv2.weight": "0.safetensors",
+    "encoder.mid_block.resnets.0.conv2.bias": "0.safetensors",
+    "encoder.mid_block.resnets.1.norm1.bias": "0.safetensors",
+    "encoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv1.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv1.bias": "0.safetensors",
+    "encoder.mid_block.resnets.1.norm2.bias": "0.safetensors",
+    "encoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv2.weight": "0.safetensors",
+    "encoder.mid_block.resnets.1.conv2.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.group_norm.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.group_norm.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_q.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_q.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_k.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_k.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_v.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_v.bias": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_out.weight": "0.safetensors",
+    "encoder.mid_block.attentions.0.to_out.bias": "0.safetensors",
+    "encoder.conv_norm_out.bias": "0.safetensors",
+    "encoder.conv_norm_out.weight": "0.safetensors",
+    "encoder.conv_out.weight": "0.safetensors",
+    "encoder.conv_out.bias": "0.safetensors",
+    "decoder.conv_in.weight": "0.safetensors",
+    "decoder.conv_in.bias": "0.safetensors",
+    "decoder.mid_block.resnets.0.norm1.bias": "0.safetensors",
+    "decoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv1.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv1.bias": "0.safetensors",
+    "decoder.mid_block.resnets.0.norm2.bias": "0.safetensors",
+    "decoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv2.weight": "0.safetensors",
+    "decoder.mid_block.resnets.0.conv2.bias": "0.safetensors",
+    "decoder.mid_block.resnets.1.norm1.bias": "0.safetensors",
+    "decoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv1.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv1.bias": "0.safetensors",
+    "decoder.mid_block.resnets.1.norm2.bias": "0.safetensors",
+    "decoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv2.weight": "0.safetensors",
+    "decoder.mid_block.resnets.1.conv2.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.group_norm.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.group_norm.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_q.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_q.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_k.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_k.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_v.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_v.bias": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_out.weight": "0.safetensors",
+    "decoder.mid_block.attentions.0.to_out.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.0.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.1.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.0.resnets.2.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.0.upsamplers.0.conv.weight": "0.safetensors",
+    "decoder.up_blocks.0.upsamplers.0.conv.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.0.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.1.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.1.resnets.2.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.1.upsamplers.0.conv.weight": "0.safetensors",
+    "decoder.up_blocks.1.upsamplers.0.conv.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.1.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.2.resnets.2.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.2.upsamplers.0.conv.weight": "0.safetensors",
+    "decoder.up_blocks.2.upsamplers.0.conv.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.1.conv2.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.norm1.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.norm1.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.conv1.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.conv1.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.norm2.bias": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.norm2.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.conv2.weight": "0.safetensors",
+    "decoder.up_blocks.3.resnets.2.conv2.bias": "0.safetensors",
+    "decoder.conv_norm_out.bias": "0.safetensors",
+    "decoder.conv_norm_out.weight": "0.safetensors",
+    "decoder.conv_out.weight": "0.safetensors",
+    "decoder.conv_out.bias": "0.safetensors",
+    "quant_conv.weight": "0.safetensors",
+    "quant_conv.bias": "0.safetensors",
+    "post_quant_conv.weight": "0.safetensors",
+    "post_quant_conv.bias": "0.safetensors",
+    "bn.running_mean": "0.safetensors",
+    "bn.running_var": "0.safetensors"
+  }
+}