| { |
| "parent_sha256": "04b1c301231dd422b8860db31311ab2721511346a32cb1e079c4c4e5f1fe4696", |
| "sha256": "aa364f2a0e1d96b7ffb69e52bbdd4f1f07634ce27d10d3686ffff0c90824f7dd", |
| "original_layers": 24, |
| "kept_layers": [ |
| 0, |
| 1, |
| 2, |
| 3, |
| 4, |
| 5, |
| 6, |
| 7, |
| 8, |
| 9, |
| 10, |
| 11, |
| 12, |
| 13, |
| 14, |
| 15, |
| 16, |
| 17, |
| 18, |
| 19, |
| 20, |
| 21, |
| 22, |
| 23 |
| ], |
| "dropped_layers": [], |
| "removed_nontext_tensors": [ |
| "model.visual.blocks.0.attn.proj.bias", |
| "model.visual.blocks.0.attn.proj.weight", |
| "model.visual.blocks.0.attn.qkv.bias", |
| "model.visual.blocks.0.attn.qkv.weight", |
| "model.visual.blocks.0.mlp.linear_fc1.bias", |
| "model.visual.blocks.0.mlp.linear_fc1.weight", |
| "model.visual.blocks.0.mlp.linear_fc2.bias", |
| "model.visual.blocks.0.mlp.linear_fc2.weight", |
| "model.visual.blocks.0.norm1.bias", |
| "model.visual.blocks.0.norm1.weight", |
| "model.visual.blocks.0.norm2.bias", |
| "model.visual.blocks.0.norm2.weight", |
| "model.visual.blocks.1.attn.proj.bias", |
| "model.visual.blocks.1.attn.proj.weight", |
| "model.visual.blocks.1.attn.qkv.bias", |
| "model.visual.blocks.1.attn.qkv.weight", |
| "model.visual.blocks.1.mlp.linear_fc1.bias", |
| "model.visual.blocks.1.mlp.linear_fc1.weight", |
| "model.visual.blocks.1.mlp.linear_fc2.bias", |
| "model.visual.blocks.1.mlp.linear_fc2.weight", |
| "model.visual.blocks.1.norm1.bias", |
| "model.visual.blocks.1.norm1.weight", |
| "model.visual.blocks.1.norm2.bias", |
| "model.visual.blocks.1.norm2.weight", |
| "model.visual.blocks.10.attn.proj.bias", |
| "model.visual.blocks.10.attn.proj.weight", |
| "model.visual.blocks.10.attn.qkv.bias", |
| "model.visual.blocks.10.attn.qkv.weight", |
| "model.visual.blocks.10.mlp.linear_fc1.bias", |
| "model.visual.blocks.10.mlp.linear_fc1.weight", |
| "model.visual.blocks.10.mlp.linear_fc2.bias", |
| "model.visual.blocks.10.mlp.linear_fc2.weight", |
| "model.visual.blocks.10.norm1.bias", |
| "model.visual.blocks.10.norm1.weight", |
| "model.visual.blocks.10.norm2.bias", |
| "model.visual.blocks.10.norm2.weight", |
| "model.visual.blocks.11.attn.proj.bias", |
| "model.visual.blocks.11.attn.proj.weight", |
| "model.visual.blocks.11.attn.qkv.bias", |
| "model.visual.blocks.11.attn.qkv.weight", |
| "model.visual.blocks.11.mlp.linear_fc1.bias", |
| "model.visual.blocks.11.mlp.linear_fc1.weight", |
| "model.visual.blocks.11.mlp.linear_fc2.bias", |
| "model.visual.blocks.11.mlp.linear_fc2.weight", |
| "model.visual.blocks.11.norm1.bias", |
| "model.visual.blocks.11.norm1.weight", |
| "model.visual.blocks.11.norm2.bias", |
| "model.visual.blocks.11.norm2.weight", |
| "model.visual.blocks.2.attn.proj.bias", |
| "model.visual.blocks.2.attn.proj.weight", |
| "model.visual.blocks.2.attn.qkv.bias", |
| "model.visual.blocks.2.attn.qkv.weight", |
| "model.visual.blocks.2.mlp.linear_fc1.bias", |
| "model.visual.blocks.2.mlp.linear_fc1.weight", |
| "model.visual.blocks.2.mlp.linear_fc2.bias", |
| "model.visual.blocks.2.mlp.linear_fc2.weight", |
| "model.visual.blocks.2.norm1.bias", |
| "model.visual.blocks.2.norm1.weight", |
| "model.visual.blocks.2.norm2.bias", |
| "model.visual.blocks.2.norm2.weight", |
| "model.visual.blocks.3.attn.proj.bias", |
| "model.visual.blocks.3.attn.proj.weight", |
| "model.visual.blocks.3.attn.qkv.bias", |
| "model.visual.blocks.3.attn.qkv.weight", |
| "model.visual.blocks.3.mlp.linear_fc1.bias", |
| "model.visual.blocks.3.mlp.linear_fc1.weight", |
| "model.visual.blocks.3.mlp.linear_fc2.bias", |
| "model.visual.blocks.3.mlp.linear_fc2.weight", |
| "model.visual.blocks.3.norm1.bias", |
| "model.visual.blocks.3.norm1.weight", |
| "model.visual.blocks.3.norm2.bias", |
| "model.visual.blocks.3.norm2.weight", |
| "model.visual.blocks.4.attn.proj.bias", |
| "model.visual.blocks.4.attn.proj.weight", |
| "model.visual.blocks.4.attn.qkv.bias", |
| "model.visual.blocks.4.attn.qkv.weight", |
| "model.visual.blocks.4.mlp.linear_fc1.bias", |
| "model.visual.blocks.4.mlp.linear_fc1.weight", |
| "model.visual.blocks.4.mlp.linear_fc2.bias", |
| "model.visual.blocks.4.mlp.linear_fc2.weight", |
| "model.visual.blocks.4.norm1.bias", |
| "model.visual.blocks.4.norm1.weight", |
| "model.visual.blocks.4.norm2.bias", |
| "model.visual.blocks.4.norm2.weight", |
| "model.visual.blocks.5.attn.proj.bias", |
| "model.visual.blocks.5.attn.proj.weight", |
| "model.visual.blocks.5.attn.qkv.bias", |
| "model.visual.blocks.5.attn.qkv.weight", |
| "model.visual.blocks.5.mlp.linear_fc1.bias", |
| "model.visual.blocks.5.mlp.linear_fc1.weight", |
| "model.visual.blocks.5.mlp.linear_fc2.bias", |
| "model.visual.blocks.5.mlp.linear_fc2.weight", |
| "model.visual.blocks.5.norm1.bias", |
| "model.visual.blocks.5.norm1.weight", |
| "model.visual.blocks.5.norm2.bias", |
| "model.visual.blocks.5.norm2.weight", |
| "model.visual.blocks.6.attn.proj.bias", |
| "model.visual.blocks.6.attn.proj.weight", |
| "model.visual.blocks.6.attn.qkv.bias", |
| "model.visual.blocks.6.attn.qkv.weight", |
| "model.visual.blocks.6.mlp.linear_fc1.bias", |
| "model.visual.blocks.6.mlp.linear_fc1.weight", |
| "model.visual.blocks.6.mlp.linear_fc2.bias", |
| "model.visual.blocks.6.mlp.linear_fc2.weight", |
| "model.visual.blocks.6.norm1.bias", |
| "model.visual.blocks.6.norm1.weight", |
| "model.visual.blocks.6.norm2.bias", |
| "model.visual.blocks.6.norm2.weight", |
| "model.visual.blocks.7.attn.proj.bias", |
| "model.visual.blocks.7.attn.proj.weight", |
| "model.visual.blocks.7.attn.qkv.bias", |
| "model.visual.blocks.7.attn.qkv.weight", |
| "model.visual.blocks.7.mlp.linear_fc1.bias", |
| "model.visual.blocks.7.mlp.linear_fc1.weight", |
| "model.visual.blocks.7.mlp.linear_fc2.bias", |
| "model.visual.blocks.7.mlp.linear_fc2.weight", |
| "model.visual.blocks.7.norm1.bias", |
| "model.visual.blocks.7.norm1.weight", |
| "model.visual.blocks.7.norm2.bias", |
| "model.visual.blocks.7.norm2.weight", |
| "model.visual.blocks.8.attn.proj.bias", |
| "model.visual.blocks.8.attn.proj.weight", |
| "model.visual.blocks.8.attn.qkv.bias", |
| "model.visual.blocks.8.attn.qkv.weight", |
| "model.visual.blocks.8.mlp.linear_fc1.bias", |
| "model.visual.blocks.8.mlp.linear_fc1.weight", |
| "model.visual.blocks.8.mlp.linear_fc2.bias", |
| "model.visual.blocks.8.mlp.linear_fc2.weight", |
| "model.visual.blocks.8.norm1.bias", |
| "model.visual.blocks.8.norm1.weight", |
| "model.visual.blocks.8.norm2.bias", |
| "model.visual.blocks.8.norm2.weight", |
| "model.visual.blocks.9.attn.proj.bias", |
| "model.visual.blocks.9.attn.proj.weight", |
| "model.visual.blocks.9.attn.qkv.bias", |
| "model.visual.blocks.9.attn.qkv.weight", |
| "model.visual.blocks.9.mlp.linear_fc1.bias", |
| "model.visual.blocks.9.mlp.linear_fc1.weight", |
| "model.visual.blocks.9.mlp.linear_fc2.bias", |
| "model.visual.blocks.9.mlp.linear_fc2.weight", |
| "model.visual.blocks.9.norm1.bias", |
| "model.visual.blocks.9.norm1.weight", |
| "model.visual.blocks.9.norm2.bias", |
| "model.visual.blocks.9.norm2.weight", |
| "model.visual.merger.linear_fc1.bias", |
| "model.visual.merger.linear_fc1.weight", |
| "model.visual.merger.linear_fc2.bias", |
| "model.visual.merger.linear_fc2.weight", |
| "model.visual.merger.norm.bias", |
| "model.visual.merger.norm.weight", |
| "model.visual.patch_embed.proj.bias", |
| "model.visual.patch_embed.proj.weight", |
| "model.visual.pos_embed.weight", |
| "mtp.fc.weight", |
| "mtp.layers.0.input_layernorm.weight", |
| "mtp.layers.0.mlp.down_proj.weight", |
| "mtp.layers.0.mlp.gate_proj.weight", |
| "mtp.layers.0.mlp.up_proj.weight", |
| "mtp.layers.0.post_attention_layernorm.weight", |
| "mtp.layers.0.self_attn.k_norm.weight", |
| "mtp.layers.0.self_attn.k_proj.weight", |
| "mtp.layers.0.self_attn.o_proj.weight", |
| "mtp.layers.0.self_attn.q_norm.weight", |
| "mtp.layers.0.self_attn.q_proj.weight", |
| "mtp.layers.0.self_attn.v_proj.weight", |
| "mtp.norm.weight", |
| "mtp.pre_fc_norm_embedding.weight", |
| "mtp.pre_fc_norm_hidden.weight" |
| ], |
| "source_bytes": 1746942600, |
| "checkpoint_bytes": 1504827552, |
| "parameters": 752393024, |
| "mapping": { |
| "model.layers.0.linear_attn.A_log": "model.language_model.layers.0.linear_attn.A_log", |
| "model.layers.0.linear_attn.norm.weight": "model.language_model.layers.0.linear_attn.norm.weight", |
| "model.layers.1.linear_attn.A_log": "model.language_model.layers.1.linear_attn.A_log", |
| "model.layers.1.linear_attn.norm.weight": "model.language_model.layers.1.linear_attn.norm.weight", |
| "model.layers.10.linear_attn.A_log": "model.language_model.layers.10.linear_attn.A_log", |
| "model.layers.10.linear_attn.norm.weight": "model.language_model.layers.10.linear_attn.norm.weight", |
| "model.layers.12.linear_attn.A_log": "model.language_model.layers.12.linear_attn.A_log", |
| "model.layers.12.linear_attn.norm.weight": "model.language_model.layers.12.linear_attn.norm.weight", |
| "model.layers.13.linear_attn.A_log": "model.language_model.layers.13.linear_attn.A_log", |
| "model.layers.13.linear_attn.norm.weight": "model.language_model.layers.13.linear_attn.norm.weight", |
| "model.layers.14.linear_attn.A_log": "model.language_model.layers.14.linear_attn.A_log", |
| "model.layers.14.linear_attn.norm.weight": "model.language_model.layers.14.linear_attn.norm.weight", |
| "model.layers.16.linear_attn.A_log": "model.language_model.layers.16.linear_attn.A_log", |
| "model.layers.16.linear_attn.norm.weight": "model.language_model.layers.16.linear_attn.norm.weight", |
| "model.layers.17.linear_attn.A_log": "model.language_model.layers.17.linear_attn.A_log", |
| "model.layers.17.linear_attn.norm.weight": "model.language_model.layers.17.linear_attn.norm.weight", |
| "model.layers.18.linear_attn.A_log": "model.language_model.layers.18.linear_attn.A_log", |
| "model.layers.18.linear_attn.norm.weight": "model.language_model.layers.18.linear_attn.norm.weight", |
| "model.layers.2.linear_attn.A_log": "model.language_model.layers.2.linear_attn.A_log", |
| "model.layers.2.linear_attn.norm.weight": "model.language_model.layers.2.linear_attn.norm.weight", |
| "model.layers.20.linear_attn.A_log": "model.language_model.layers.20.linear_attn.A_log", |
| "model.layers.20.linear_attn.norm.weight": "model.language_model.layers.20.linear_attn.norm.weight", |
| "model.layers.21.linear_attn.A_log": "model.language_model.layers.21.linear_attn.A_log", |
| "model.layers.21.linear_attn.norm.weight": "model.language_model.layers.21.linear_attn.norm.weight", |
| "model.layers.22.linear_attn.A_log": "model.language_model.layers.22.linear_attn.A_log", |
| "model.layers.22.linear_attn.norm.weight": "model.language_model.layers.22.linear_attn.norm.weight", |
| "model.layers.4.linear_attn.A_log": "model.language_model.layers.4.linear_attn.A_log", |
| "model.layers.4.linear_attn.norm.weight": "model.language_model.layers.4.linear_attn.norm.weight", |
| "model.layers.5.linear_attn.A_log": "model.language_model.layers.5.linear_attn.A_log", |
| "model.layers.5.linear_attn.norm.weight": "model.language_model.layers.5.linear_attn.norm.weight", |
| "model.layers.6.linear_attn.A_log": "model.language_model.layers.6.linear_attn.A_log", |
| "model.layers.6.linear_attn.norm.weight": "model.language_model.layers.6.linear_attn.norm.weight", |
| "model.layers.8.linear_attn.A_log": "model.language_model.layers.8.linear_attn.A_log", |
| "model.layers.8.linear_attn.norm.weight": "model.language_model.layers.8.linear_attn.norm.weight", |
| "model.layers.9.linear_attn.A_log": "model.language_model.layers.9.linear_attn.A_log", |
| "model.layers.9.linear_attn.norm.weight": "model.language_model.layers.9.linear_attn.norm.weight", |
| "model.embed_tokens.weight": "model.language_model.embed_tokens.weight", |
| "model.layers.0.input_layernorm.weight": "model.language_model.layers.0.input_layernorm.weight", |
| "model.layers.0.linear_attn.conv1d.weight": "model.language_model.layers.0.linear_attn.conv1d.weight", |
| "model.layers.0.linear_attn.dt_bias": "model.language_model.layers.0.linear_attn.dt_bias", |
| "model.layers.0.linear_attn.in_proj_a.weight": "model.language_model.layers.0.linear_attn.in_proj_a.weight", |
| "model.layers.0.linear_attn.in_proj_b.weight": "model.language_model.layers.0.linear_attn.in_proj_b.weight", |
| "model.layers.0.linear_attn.in_proj_qkv.weight": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight", |
| "model.layers.0.linear_attn.in_proj_z.weight": "model.language_model.layers.0.linear_attn.in_proj_z.weight", |
| "model.layers.0.linear_attn.out_proj.weight": "model.language_model.layers.0.linear_attn.out_proj.weight", |
| "model.layers.0.mlp.down_proj.weight": "model.language_model.layers.0.mlp.down_proj.weight", |
| "model.layers.0.mlp.gate_proj.weight": "model.language_model.layers.0.mlp.gate_proj.weight", |
| "model.layers.0.mlp.up_proj.weight": "model.language_model.layers.0.mlp.up_proj.weight", |
| "model.layers.0.post_attention_layernorm.weight": "model.language_model.layers.0.post_attention_layernorm.weight", |
| "model.layers.1.input_layernorm.weight": "model.language_model.layers.1.input_layernorm.weight", |
| "model.layers.1.linear_attn.conv1d.weight": "model.language_model.layers.1.linear_attn.conv1d.weight", |
| "model.layers.1.linear_attn.dt_bias": "model.language_model.layers.1.linear_attn.dt_bias", |
| "model.layers.1.linear_attn.in_proj_a.weight": "model.language_model.layers.1.linear_attn.in_proj_a.weight", |
| "model.layers.1.linear_attn.in_proj_b.weight": "model.language_model.layers.1.linear_attn.in_proj_b.weight", |
| "model.layers.1.linear_attn.in_proj_qkv.weight": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight", |
| "model.layers.1.linear_attn.in_proj_z.weight": "model.language_model.layers.1.linear_attn.in_proj_z.weight", |
| "model.layers.1.linear_attn.out_proj.weight": "model.language_model.layers.1.linear_attn.out_proj.weight", |
| "model.layers.1.mlp.down_proj.weight": "model.language_model.layers.1.mlp.down_proj.weight", |
| "model.layers.1.mlp.gate_proj.weight": "model.language_model.layers.1.mlp.gate_proj.weight", |
| "model.layers.1.mlp.up_proj.weight": "model.language_model.layers.1.mlp.up_proj.weight", |
| "model.layers.1.post_attention_layernorm.weight": "model.language_model.layers.1.post_attention_layernorm.weight", |
| "model.layers.10.input_layernorm.weight": "model.language_model.layers.10.input_layernorm.weight", |
| "model.layers.10.linear_attn.conv1d.weight": "model.language_model.layers.10.linear_attn.conv1d.weight", |
| "model.layers.10.linear_attn.dt_bias": "model.language_model.layers.10.linear_attn.dt_bias", |
| "model.layers.10.linear_attn.in_proj_a.weight": "model.language_model.layers.10.linear_attn.in_proj_a.weight", |
| "model.layers.10.linear_attn.in_proj_b.weight": "model.language_model.layers.10.linear_attn.in_proj_b.weight", |
| "model.layers.10.linear_attn.in_proj_qkv.weight": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight", |
| "model.layers.10.linear_attn.in_proj_z.weight": "model.language_model.layers.10.linear_attn.in_proj_z.weight", |
| "model.layers.10.linear_attn.out_proj.weight": "model.language_model.layers.10.linear_attn.out_proj.weight", |
| "model.layers.10.mlp.down_proj.weight": "model.language_model.layers.10.mlp.down_proj.weight", |
| "model.layers.10.mlp.gate_proj.weight": "model.language_model.layers.10.mlp.gate_proj.weight", |
| "model.layers.10.mlp.up_proj.weight": "model.language_model.layers.10.mlp.up_proj.weight", |
| "model.layers.10.post_attention_layernorm.weight": "model.language_model.layers.10.post_attention_layernorm.weight", |
| "model.layers.11.input_layernorm.weight": "model.language_model.layers.11.input_layernorm.weight", |
| "model.layers.11.mlp.down_proj.weight": "model.language_model.layers.11.mlp.down_proj.weight", |
| "model.layers.11.mlp.gate_proj.weight": "model.language_model.layers.11.mlp.gate_proj.weight", |
| "model.layers.11.mlp.up_proj.weight": "model.language_model.layers.11.mlp.up_proj.weight", |
| "model.layers.11.post_attention_layernorm.weight": "model.language_model.layers.11.post_attention_layernorm.weight", |
| "model.layers.11.self_attn.k_norm.weight": "model.language_model.layers.11.self_attn.k_norm.weight", |
| "model.layers.11.self_attn.k_proj.weight": "model.language_model.layers.11.self_attn.k_proj.weight", |
| "model.layers.11.self_attn.o_proj.weight": "model.language_model.layers.11.self_attn.o_proj.weight", |
| "model.layers.11.self_attn.q_norm.weight": "model.language_model.layers.11.self_attn.q_norm.weight", |
| "model.layers.11.self_attn.q_proj.weight": "model.language_model.layers.11.self_attn.q_proj.weight", |
| "model.layers.11.self_attn.v_proj.weight": "model.language_model.layers.11.self_attn.v_proj.weight", |
| "model.layers.12.input_layernorm.weight": "model.language_model.layers.12.input_layernorm.weight", |
| "model.layers.12.linear_attn.conv1d.weight": "model.language_model.layers.12.linear_attn.conv1d.weight", |
| "model.layers.12.linear_attn.dt_bias": "model.language_model.layers.12.linear_attn.dt_bias", |
| "model.layers.12.linear_attn.in_proj_a.weight": "model.language_model.layers.12.linear_attn.in_proj_a.weight", |
| "model.layers.12.linear_attn.in_proj_b.weight": "model.language_model.layers.12.linear_attn.in_proj_b.weight", |
| "model.layers.12.linear_attn.in_proj_qkv.weight": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight", |
| "model.layers.12.linear_attn.in_proj_z.weight": "model.language_model.layers.12.linear_attn.in_proj_z.weight", |
| "model.layers.12.linear_attn.out_proj.weight": "model.language_model.layers.12.linear_attn.out_proj.weight", |
| "model.layers.12.mlp.down_proj.weight": "model.language_model.layers.12.mlp.down_proj.weight", |
| "model.layers.12.mlp.gate_proj.weight": "model.language_model.layers.12.mlp.gate_proj.weight", |
| "model.layers.12.mlp.up_proj.weight": "model.language_model.layers.12.mlp.up_proj.weight", |
| "model.layers.12.post_attention_layernorm.weight": "model.language_model.layers.12.post_attention_layernorm.weight", |
| "model.layers.13.input_layernorm.weight": "model.language_model.layers.13.input_layernorm.weight", |
| "model.layers.13.linear_attn.conv1d.weight": "model.language_model.layers.13.linear_attn.conv1d.weight", |
| "model.layers.13.linear_attn.dt_bias": "model.language_model.layers.13.linear_attn.dt_bias", |
| "model.layers.13.linear_attn.in_proj_a.weight": "model.language_model.layers.13.linear_attn.in_proj_a.weight", |
| "model.layers.13.linear_attn.in_proj_b.weight": "model.language_model.layers.13.linear_attn.in_proj_b.weight", |
| "model.layers.13.linear_attn.in_proj_qkv.weight": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight", |
| "model.layers.13.linear_attn.in_proj_z.weight": "model.language_model.layers.13.linear_attn.in_proj_z.weight", |
| "model.layers.13.linear_attn.out_proj.weight": "model.language_model.layers.13.linear_attn.out_proj.weight", |
| "model.layers.13.mlp.down_proj.weight": "model.language_model.layers.13.mlp.down_proj.weight", |
| "model.layers.13.mlp.gate_proj.weight": "model.language_model.layers.13.mlp.gate_proj.weight", |
| "model.layers.13.mlp.up_proj.weight": "model.language_model.layers.13.mlp.up_proj.weight", |
| "model.layers.13.post_attention_layernorm.weight": "model.language_model.layers.13.post_attention_layernorm.weight", |
| "model.layers.14.input_layernorm.weight": "model.language_model.layers.14.input_layernorm.weight", |
| "model.layers.14.linear_attn.conv1d.weight": "model.language_model.layers.14.linear_attn.conv1d.weight", |
| "model.layers.14.linear_attn.dt_bias": "model.language_model.layers.14.linear_attn.dt_bias", |
| "model.layers.14.linear_attn.in_proj_a.weight": "model.language_model.layers.14.linear_attn.in_proj_a.weight", |
| "model.layers.14.linear_attn.in_proj_b.weight": "model.language_model.layers.14.linear_attn.in_proj_b.weight", |
| "model.layers.14.linear_attn.in_proj_qkv.weight": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight", |
| "model.layers.14.linear_attn.in_proj_z.weight": "model.language_model.layers.14.linear_attn.in_proj_z.weight", |
| "model.layers.14.linear_attn.out_proj.weight": "model.language_model.layers.14.linear_attn.out_proj.weight", |
| "model.layers.14.mlp.down_proj.weight": "model.language_model.layers.14.mlp.down_proj.weight", |
| "model.layers.14.mlp.gate_proj.weight": "model.language_model.layers.14.mlp.gate_proj.weight", |
| "model.layers.14.mlp.up_proj.weight": "model.language_model.layers.14.mlp.up_proj.weight", |
| "model.layers.14.post_attention_layernorm.weight": "model.language_model.layers.14.post_attention_layernorm.weight", |
| "model.layers.15.input_layernorm.weight": "model.language_model.layers.15.input_layernorm.weight", |
| "model.layers.15.mlp.down_proj.weight": "model.language_model.layers.15.mlp.down_proj.weight", |
| "model.layers.15.mlp.gate_proj.weight": "model.language_model.layers.15.mlp.gate_proj.weight", |
| "model.layers.15.mlp.up_proj.weight": "model.language_model.layers.15.mlp.up_proj.weight", |
| "model.layers.15.post_attention_layernorm.weight": "model.language_model.layers.15.post_attention_layernorm.weight", |
| "model.layers.15.self_attn.k_norm.weight": "model.language_model.layers.15.self_attn.k_norm.weight", |
| "model.layers.15.self_attn.k_proj.weight": "model.language_model.layers.15.self_attn.k_proj.weight", |
| "model.layers.15.self_attn.o_proj.weight": "model.language_model.layers.15.self_attn.o_proj.weight", |
| "model.layers.15.self_attn.q_norm.weight": "model.language_model.layers.15.self_attn.q_norm.weight", |
| "model.layers.15.self_attn.q_proj.weight": "model.language_model.layers.15.self_attn.q_proj.weight", |
| "model.layers.15.self_attn.v_proj.weight": "model.language_model.layers.15.self_attn.v_proj.weight", |
| "model.layers.16.input_layernorm.weight": "model.language_model.layers.16.input_layernorm.weight", |
| "model.layers.16.linear_attn.conv1d.weight": "model.language_model.layers.16.linear_attn.conv1d.weight", |
| "model.layers.16.linear_attn.dt_bias": "model.language_model.layers.16.linear_attn.dt_bias", |
| "model.layers.16.linear_attn.in_proj_a.weight": "model.language_model.layers.16.linear_attn.in_proj_a.weight", |
| "model.layers.16.linear_attn.in_proj_b.weight": "model.language_model.layers.16.linear_attn.in_proj_b.weight", |
| "model.layers.16.linear_attn.in_proj_qkv.weight": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight", |
| "model.layers.16.linear_attn.in_proj_z.weight": "model.language_model.layers.16.linear_attn.in_proj_z.weight", |
| "model.layers.16.linear_attn.out_proj.weight": "model.language_model.layers.16.linear_attn.out_proj.weight", |
| "model.layers.16.mlp.down_proj.weight": "model.language_model.layers.16.mlp.down_proj.weight", |
| "model.layers.16.mlp.gate_proj.weight": "model.language_model.layers.16.mlp.gate_proj.weight", |
| "model.layers.16.mlp.up_proj.weight": "model.language_model.layers.16.mlp.up_proj.weight", |
| "model.layers.16.post_attention_layernorm.weight": "model.language_model.layers.16.post_attention_layernorm.weight", |
| "model.layers.17.input_layernorm.weight": "model.language_model.layers.17.input_layernorm.weight", |
| "model.layers.17.linear_attn.conv1d.weight": "model.language_model.layers.17.linear_attn.conv1d.weight", |
| "model.layers.17.linear_attn.dt_bias": "model.language_model.layers.17.linear_attn.dt_bias", |
| "model.layers.17.linear_attn.in_proj_a.weight": "model.language_model.layers.17.linear_attn.in_proj_a.weight", |
| "model.layers.17.linear_attn.in_proj_b.weight": "model.language_model.layers.17.linear_attn.in_proj_b.weight", |
| "model.layers.17.linear_attn.in_proj_qkv.weight": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight", |
| "model.layers.17.linear_attn.in_proj_z.weight": "model.language_model.layers.17.linear_attn.in_proj_z.weight", |
| "model.layers.17.linear_attn.out_proj.weight": "model.language_model.layers.17.linear_attn.out_proj.weight", |
| "model.layers.17.mlp.down_proj.weight": "model.language_model.layers.17.mlp.down_proj.weight", |
| "model.layers.17.mlp.gate_proj.weight": "model.language_model.layers.17.mlp.gate_proj.weight", |
| "model.layers.17.mlp.up_proj.weight": "model.language_model.layers.17.mlp.up_proj.weight", |
| "model.layers.17.post_attention_layernorm.weight": "model.language_model.layers.17.post_attention_layernorm.weight", |
| "model.layers.18.input_layernorm.weight": "model.language_model.layers.18.input_layernorm.weight", |
| "model.layers.18.linear_attn.conv1d.weight": "model.language_model.layers.18.linear_attn.conv1d.weight", |
| "model.layers.18.linear_attn.dt_bias": "model.language_model.layers.18.linear_attn.dt_bias", |
| "model.layers.18.linear_attn.in_proj_a.weight": "model.language_model.layers.18.linear_attn.in_proj_a.weight", |
| "model.layers.18.linear_attn.in_proj_b.weight": "model.language_model.layers.18.linear_attn.in_proj_b.weight", |
| "model.layers.18.linear_attn.in_proj_qkv.weight": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight", |
| "model.layers.18.linear_attn.in_proj_z.weight": "model.language_model.layers.18.linear_attn.in_proj_z.weight", |
| "model.layers.18.linear_attn.out_proj.weight": "model.language_model.layers.18.linear_attn.out_proj.weight", |
| "model.layers.18.mlp.down_proj.weight": "model.language_model.layers.18.mlp.down_proj.weight", |
| "model.layers.18.mlp.gate_proj.weight": "model.language_model.layers.18.mlp.gate_proj.weight", |
| "model.layers.18.mlp.up_proj.weight": "model.language_model.layers.18.mlp.up_proj.weight", |
| "model.layers.18.post_attention_layernorm.weight": "model.language_model.layers.18.post_attention_layernorm.weight", |
| "model.layers.19.input_layernorm.weight": "model.language_model.layers.19.input_layernorm.weight", |
| "model.layers.19.mlp.down_proj.weight": "model.language_model.layers.19.mlp.down_proj.weight", |
| "model.layers.19.mlp.gate_proj.weight": "model.language_model.layers.19.mlp.gate_proj.weight", |
| "model.layers.19.mlp.up_proj.weight": "model.language_model.layers.19.mlp.up_proj.weight", |
| "model.layers.19.post_attention_layernorm.weight": "model.language_model.layers.19.post_attention_layernorm.weight", |
| "model.layers.19.self_attn.k_norm.weight": "model.language_model.layers.19.self_attn.k_norm.weight", |
| "model.layers.19.self_attn.k_proj.weight": "model.language_model.layers.19.self_attn.k_proj.weight", |
| "model.layers.19.self_attn.o_proj.weight": "model.language_model.layers.19.self_attn.o_proj.weight", |
| "model.layers.19.self_attn.q_norm.weight": "model.language_model.layers.19.self_attn.q_norm.weight", |
| "model.layers.19.self_attn.q_proj.weight": "model.language_model.layers.19.self_attn.q_proj.weight", |
| "model.layers.19.self_attn.v_proj.weight": "model.language_model.layers.19.self_attn.v_proj.weight", |
| "model.layers.2.input_layernorm.weight": "model.language_model.layers.2.input_layernorm.weight", |
| "model.layers.2.linear_attn.conv1d.weight": "model.language_model.layers.2.linear_attn.conv1d.weight", |
| "model.layers.2.linear_attn.dt_bias": "model.language_model.layers.2.linear_attn.dt_bias", |
| "model.layers.2.linear_attn.in_proj_a.weight": "model.language_model.layers.2.linear_attn.in_proj_a.weight", |
| "model.layers.2.linear_attn.in_proj_b.weight": "model.language_model.layers.2.linear_attn.in_proj_b.weight", |
| "model.layers.2.linear_attn.in_proj_qkv.weight": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight", |
| "model.layers.2.linear_attn.in_proj_z.weight": "model.language_model.layers.2.linear_attn.in_proj_z.weight", |
| "model.layers.2.linear_attn.out_proj.weight": "model.language_model.layers.2.linear_attn.out_proj.weight", |
| "model.layers.2.mlp.down_proj.weight": "model.language_model.layers.2.mlp.down_proj.weight", |
| "model.layers.2.mlp.gate_proj.weight": "model.language_model.layers.2.mlp.gate_proj.weight", |
| "model.layers.2.mlp.up_proj.weight": "model.language_model.layers.2.mlp.up_proj.weight", |
| "model.layers.2.post_attention_layernorm.weight": "model.language_model.layers.2.post_attention_layernorm.weight", |
| "model.layers.20.input_layernorm.weight": "model.language_model.layers.20.input_layernorm.weight", |
| "model.layers.20.linear_attn.conv1d.weight": "model.language_model.layers.20.linear_attn.conv1d.weight", |
| "model.layers.20.linear_attn.dt_bias": "model.language_model.layers.20.linear_attn.dt_bias", |
| "model.layers.20.linear_attn.in_proj_a.weight": "model.language_model.layers.20.linear_attn.in_proj_a.weight", |
| "model.layers.20.linear_attn.in_proj_b.weight": "model.language_model.layers.20.linear_attn.in_proj_b.weight", |
| "model.layers.20.linear_attn.in_proj_qkv.weight": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight", |
| "model.layers.20.linear_attn.in_proj_z.weight": "model.language_model.layers.20.linear_attn.in_proj_z.weight", |
| "model.layers.20.linear_attn.out_proj.weight": "model.language_model.layers.20.linear_attn.out_proj.weight", |
| "model.layers.20.mlp.down_proj.weight": "model.language_model.layers.20.mlp.down_proj.weight", |
| "model.layers.20.mlp.gate_proj.weight": "model.language_model.layers.20.mlp.gate_proj.weight", |
| "model.layers.20.mlp.up_proj.weight": "model.language_model.layers.20.mlp.up_proj.weight", |
| "model.layers.20.post_attention_layernorm.weight": "model.language_model.layers.20.post_attention_layernorm.weight", |
| "model.layers.21.input_layernorm.weight": "model.language_model.layers.21.input_layernorm.weight", |
| "model.layers.21.linear_attn.conv1d.weight": "model.language_model.layers.21.linear_attn.conv1d.weight", |
| "model.layers.21.linear_attn.dt_bias": "model.language_model.layers.21.linear_attn.dt_bias", |
| "model.layers.21.linear_attn.in_proj_a.weight": "model.language_model.layers.21.linear_attn.in_proj_a.weight", |
| "model.layers.21.linear_attn.in_proj_b.weight": "model.language_model.layers.21.linear_attn.in_proj_b.weight", |
| "model.layers.21.linear_attn.in_proj_qkv.weight": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight", |
| "model.layers.21.linear_attn.in_proj_z.weight": "model.language_model.layers.21.linear_attn.in_proj_z.weight", |
| "model.layers.21.linear_attn.out_proj.weight": "model.language_model.layers.21.linear_attn.out_proj.weight", |
| "model.layers.21.mlp.down_proj.weight": "model.language_model.layers.21.mlp.down_proj.weight", |
| "model.layers.21.mlp.gate_proj.weight": "model.language_model.layers.21.mlp.gate_proj.weight", |
| "model.layers.21.mlp.up_proj.weight": "model.language_model.layers.21.mlp.up_proj.weight", |
| "model.layers.21.post_attention_layernorm.weight": "model.language_model.layers.21.post_attention_layernorm.weight", |
| "model.layers.22.input_layernorm.weight": "model.language_model.layers.22.input_layernorm.weight", |
| "model.layers.22.linear_attn.conv1d.weight": "model.language_model.layers.22.linear_attn.conv1d.weight", |
| "model.layers.22.linear_attn.dt_bias": "model.language_model.layers.22.linear_attn.dt_bias", |
| "model.layers.22.linear_attn.in_proj_a.weight": "model.language_model.layers.22.linear_attn.in_proj_a.weight", |
| "model.layers.22.linear_attn.in_proj_b.weight": "model.language_model.layers.22.linear_attn.in_proj_b.weight", |
| "model.layers.22.linear_attn.in_proj_qkv.weight": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight", |
| "model.layers.22.linear_attn.in_proj_z.weight": "model.language_model.layers.22.linear_attn.in_proj_z.weight", |
| "model.layers.22.linear_attn.out_proj.weight": "model.language_model.layers.22.linear_attn.out_proj.weight", |
| "model.layers.22.mlp.down_proj.weight": "model.language_model.layers.22.mlp.down_proj.weight", |
| "model.layers.22.mlp.gate_proj.weight": "model.language_model.layers.22.mlp.gate_proj.weight", |
| "model.layers.22.mlp.up_proj.weight": "model.language_model.layers.22.mlp.up_proj.weight", |
| "model.layers.22.post_attention_layernorm.weight": "model.language_model.layers.22.post_attention_layernorm.weight", |
| "model.layers.23.input_layernorm.weight": "model.language_model.layers.23.input_layernorm.weight", |
| "model.layers.23.mlp.down_proj.weight": "model.language_model.layers.23.mlp.down_proj.weight", |
| "model.layers.23.mlp.gate_proj.weight": "model.language_model.layers.23.mlp.gate_proj.weight", |
| "model.layers.23.mlp.up_proj.weight": "model.language_model.layers.23.mlp.up_proj.weight", |
| "model.layers.23.post_attention_layernorm.weight": "model.language_model.layers.23.post_attention_layernorm.weight", |
| "model.layers.23.self_attn.k_norm.weight": "model.language_model.layers.23.self_attn.k_norm.weight", |
| "model.layers.23.self_attn.k_proj.weight": "model.language_model.layers.23.self_attn.k_proj.weight", |
| "model.layers.23.self_attn.o_proj.weight": "model.language_model.layers.23.self_attn.o_proj.weight", |
| "model.layers.23.self_attn.q_norm.weight": "model.language_model.layers.23.self_attn.q_norm.weight", |
| "model.layers.23.self_attn.q_proj.weight": "model.language_model.layers.23.self_attn.q_proj.weight", |
| "model.layers.23.self_attn.v_proj.weight": "model.language_model.layers.23.self_attn.v_proj.weight", |
| "model.layers.3.input_layernorm.weight": "model.language_model.layers.3.input_layernorm.weight", |
| "model.layers.3.mlp.down_proj.weight": "model.language_model.layers.3.mlp.down_proj.weight", |
| "model.layers.3.mlp.gate_proj.weight": "model.language_model.layers.3.mlp.gate_proj.weight", |
| "model.layers.3.mlp.up_proj.weight": "model.language_model.layers.3.mlp.up_proj.weight", |
| "model.layers.3.post_attention_layernorm.weight": "model.language_model.layers.3.post_attention_layernorm.weight", |
| "model.layers.3.self_attn.k_norm.weight": "model.language_model.layers.3.self_attn.k_norm.weight", |
| "model.layers.3.self_attn.k_proj.weight": "model.language_model.layers.3.self_attn.k_proj.weight", |
| "model.layers.3.self_attn.o_proj.weight": "model.language_model.layers.3.self_attn.o_proj.weight", |
| "model.layers.3.self_attn.q_norm.weight": "model.language_model.layers.3.self_attn.q_norm.weight", |
| "model.layers.3.self_attn.q_proj.weight": "model.language_model.layers.3.self_attn.q_proj.weight", |
| "model.layers.3.self_attn.v_proj.weight": "model.language_model.layers.3.self_attn.v_proj.weight", |
| "model.layers.4.input_layernorm.weight": "model.language_model.layers.4.input_layernorm.weight", |
| "model.layers.4.linear_attn.conv1d.weight": "model.language_model.layers.4.linear_attn.conv1d.weight", |
| "model.layers.4.linear_attn.dt_bias": "model.language_model.layers.4.linear_attn.dt_bias", |
| "model.layers.4.linear_attn.in_proj_a.weight": "model.language_model.layers.4.linear_attn.in_proj_a.weight", |
| "model.layers.4.linear_attn.in_proj_b.weight": "model.language_model.layers.4.linear_attn.in_proj_b.weight", |
| "model.layers.4.linear_attn.in_proj_qkv.weight": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight", |
| "model.layers.4.linear_attn.in_proj_z.weight": "model.language_model.layers.4.linear_attn.in_proj_z.weight", |
| "model.layers.4.linear_attn.out_proj.weight": "model.language_model.layers.4.linear_attn.out_proj.weight", |
| "model.layers.4.mlp.down_proj.weight": "model.language_model.layers.4.mlp.down_proj.weight", |
| "model.layers.4.mlp.gate_proj.weight": "model.language_model.layers.4.mlp.gate_proj.weight", |
| "model.layers.4.mlp.up_proj.weight": "model.language_model.layers.4.mlp.up_proj.weight", |
| "model.layers.4.post_attention_layernorm.weight": "model.language_model.layers.4.post_attention_layernorm.weight", |
| "model.layers.5.input_layernorm.weight": "model.language_model.layers.5.input_layernorm.weight", |
| "model.layers.5.linear_attn.conv1d.weight": "model.language_model.layers.5.linear_attn.conv1d.weight", |
| "model.layers.5.linear_attn.dt_bias": "model.language_model.layers.5.linear_attn.dt_bias", |
| "model.layers.5.linear_attn.in_proj_a.weight": "model.language_model.layers.5.linear_attn.in_proj_a.weight", |
| "model.layers.5.linear_attn.in_proj_b.weight": "model.language_model.layers.5.linear_attn.in_proj_b.weight", |
| "model.layers.5.linear_attn.in_proj_qkv.weight": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight", |
| "model.layers.5.linear_attn.in_proj_z.weight": "model.language_model.layers.5.linear_attn.in_proj_z.weight", |
| "model.layers.5.linear_attn.out_proj.weight": "model.language_model.layers.5.linear_attn.out_proj.weight", |
| "model.layers.5.mlp.down_proj.weight": "model.language_model.layers.5.mlp.down_proj.weight", |
| "model.layers.5.mlp.gate_proj.weight": "model.language_model.layers.5.mlp.gate_proj.weight", |
| "model.layers.5.mlp.up_proj.weight": "model.language_model.layers.5.mlp.up_proj.weight", |
| "model.layers.5.post_attention_layernorm.weight": "model.language_model.layers.5.post_attention_layernorm.weight", |
| "model.layers.6.input_layernorm.weight": "model.language_model.layers.6.input_layernorm.weight", |
| "model.layers.6.linear_attn.conv1d.weight": "model.language_model.layers.6.linear_attn.conv1d.weight", |
| "model.layers.6.linear_attn.dt_bias": "model.language_model.layers.6.linear_attn.dt_bias", |
| "model.layers.6.linear_attn.in_proj_a.weight": "model.language_model.layers.6.linear_attn.in_proj_a.weight", |
| "model.layers.6.linear_attn.in_proj_b.weight": "model.language_model.layers.6.linear_attn.in_proj_b.weight", |
| "model.layers.6.linear_attn.in_proj_qkv.weight": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight", |
| "model.layers.6.linear_attn.in_proj_z.weight": "model.language_model.layers.6.linear_attn.in_proj_z.weight", |
| "model.layers.6.linear_attn.out_proj.weight": "model.language_model.layers.6.linear_attn.out_proj.weight", |
| "model.layers.6.mlp.down_proj.weight": "model.language_model.layers.6.mlp.down_proj.weight", |
| "model.layers.6.mlp.gate_proj.weight": "model.language_model.layers.6.mlp.gate_proj.weight", |
| "model.layers.6.mlp.up_proj.weight": "model.language_model.layers.6.mlp.up_proj.weight", |
| "model.layers.6.post_attention_layernorm.weight": "model.language_model.layers.6.post_attention_layernorm.weight", |
| "model.layers.7.input_layernorm.weight": "model.language_model.layers.7.input_layernorm.weight", |
| "model.layers.7.mlp.down_proj.weight": "model.language_model.layers.7.mlp.down_proj.weight", |
| "model.layers.7.mlp.gate_proj.weight": "model.language_model.layers.7.mlp.gate_proj.weight", |
| "model.layers.7.mlp.up_proj.weight": "model.language_model.layers.7.mlp.up_proj.weight", |
| "model.layers.7.post_attention_layernorm.weight": "model.language_model.layers.7.post_attention_layernorm.weight", |
| "model.layers.7.self_attn.k_norm.weight": "model.language_model.layers.7.self_attn.k_norm.weight", |
| "model.layers.7.self_attn.k_proj.weight": "model.language_model.layers.7.self_attn.k_proj.weight", |
| "model.layers.7.self_attn.o_proj.weight": "model.language_model.layers.7.self_attn.o_proj.weight", |
| "model.layers.7.self_attn.q_norm.weight": "model.language_model.layers.7.self_attn.q_norm.weight", |
| "model.layers.7.self_attn.q_proj.weight": "model.language_model.layers.7.self_attn.q_proj.weight", |
| "model.layers.7.self_attn.v_proj.weight": "model.language_model.layers.7.self_attn.v_proj.weight", |
| "model.layers.8.input_layernorm.weight": "model.language_model.layers.8.input_layernorm.weight", |
| "model.layers.8.linear_attn.conv1d.weight": "model.language_model.layers.8.linear_attn.conv1d.weight", |
| "model.layers.8.linear_attn.dt_bias": "model.language_model.layers.8.linear_attn.dt_bias", |
| "model.layers.8.linear_attn.in_proj_a.weight": "model.language_model.layers.8.linear_attn.in_proj_a.weight", |
| "model.layers.8.linear_attn.in_proj_b.weight": "model.language_model.layers.8.linear_attn.in_proj_b.weight", |
| "model.layers.8.linear_attn.in_proj_qkv.weight": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight", |
| "model.layers.8.linear_attn.in_proj_z.weight": "model.language_model.layers.8.linear_attn.in_proj_z.weight", |
| "model.layers.8.linear_attn.out_proj.weight": "model.language_model.layers.8.linear_attn.out_proj.weight", |
| "model.layers.8.mlp.down_proj.weight": "model.language_model.layers.8.mlp.down_proj.weight", |
| "model.layers.8.mlp.gate_proj.weight": "model.language_model.layers.8.mlp.gate_proj.weight", |
| "model.layers.8.mlp.up_proj.weight": "model.language_model.layers.8.mlp.up_proj.weight", |
| "model.layers.8.post_attention_layernorm.weight": "model.language_model.layers.8.post_attention_layernorm.weight", |
| "model.layers.9.input_layernorm.weight": "model.language_model.layers.9.input_layernorm.weight", |
| "model.layers.9.linear_attn.conv1d.weight": "model.language_model.layers.9.linear_attn.conv1d.weight", |
| "model.layers.9.linear_attn.dt_bias": "model.language_model.layers.9.linear_attn.dt_bias", |
| "model.layers.9.linear_attn.in_proj_a.weight": "model.language_model.layers.9.linear_attn.in_proj_a.weight", |
| "model.layers.9.linear_attn.in_proj_b.weight": "model.language_model.layers.9.linear_attn.in_proj_b.weight", |
| "model.layers.9.linear_attn.in_proj_qkv.weight": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight", |
| "model.layers.9.linear_attn.in_proj_z.weight": "model.language_model.layers.9.linear_attn.in_proj_z.weight", |
| "model.layers.9.linear_attn.out_proj.weight": "model.language_model.layers.9.linear_attn.out_proj.weight", |
| "model.layers.9.mlp.down_proj.weight": "model.language_model.layers.9.mlp.down_proj.weight", |
| "model.layers.9.mlp.gate_proj.weight": "model.language_model.layers.9.mlp.gate_proj.weight", |
| "model.layers.9.mlp.up_proj.weight": "model.language_model.layers.9.mlp.up_proj.weight", |
| "model.layers.9.post_attention_layernorm.weight": "model.language_model.layers.9.post_attention_layernorm.weight", |
| "model.norm.weight": "model.language_model.norm.weight" |
| } |
| } |
|
|
