Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- .ipynb_checkpoints/model.safetensors.index-checkpoint.json +1 -0
- README.md +46 -0
- config.json +37 -0
- mergekit_config.yml +12 -0
- model-00001-of-00044.safetensors +3 -0
- model-00002-of-00044.safetensors +3 -0
- model-00003-of-00044.safetensors +3 -0
- model-00004-of-00044.safetensors +3 -0
- model-00005-of-00044.safetensors +3 -0
- model-00006-of-00044.safetensors +3 -0
- model-00007-of-00044.safetensors +3 -0
- model-00008-of-00044.safetensors +3 -0
- model-00009-of-00044.safetensors +3 -0
- model-00010-of-00044.safetensors +3 -0
- model-00011-of-00044.safetensors +3 -0
- model-00012-of-00044.safetensors +3 -0
- model-00013-of-00044.safetensors +3 -0
- model-00014-of-00044.safetensors +3 -0
- model-00015-of-00044.safetensors +3 -0
- model-00016-of-00044.safetensors +3 -0
- model-00017-of-00044.safetensors +3 -0
- model-00018-of-00044.safetensors +3 -0
- model-00019-of-00044.safetensors +3 -0
- model-00020-of-00044.safetensors +3 -0
- model-00021-of-00044.safetensors +3 -0
- model-00022-of-00044.safetensors +3 -0
- model-00023-of-00044.safetensors +3 -0
- model-00024-of-00044.safetensors +3 -0
- model-00025-of-00044.safetensors +3 -0
- model-00026-of-00044.safetensors +3 -0
- model-00027-of-00044.safetensors +3 -0
- model-00028-of-00044.safetensors +3 -0
- model-00029-of-00044.safetensors +3 -0
- model-00030-of-00044.safetensors +3 -0
- model-00031-of-00044.safetensors +3 -0
- model-00032-of-00044.safetensors +3 -0
- model-00033-of-00044.safetensors +3 -0
- model-00034-of-00044.safetensors +3 -0
- model-00035-of-00044.safetensors +3 -0
- model-00036-of-00044.safetensors +3 -0
- model-00037-of-00044.safetensors +3 -0
- model-00038-of-00044.safetensors +3 -0
- model-00039-of-00044.safetensors +3 -0
- model-00040-of-00044.safetensors +3 -0
- model-00041-of-00044.safetensors +3 -0
- model-00042-of-00044.safetensors +3 -0
- model-00043-of-00044.safetensors +3 -0
- model-00044-of-00044.safetensors +3 -0
- model.safetensors.index.json +1 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/model.safetensors.index-checkpoint.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00044.safetensors", "model.embed_tokens.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors"}}
|
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- TheDrummer/Anubis-70B-v1.1
|
| 4 |
+
- sophosympatheia/Strawberrylemonade-L3-70B-v1.2
|
| 5 |
+
- Sao10K/L3.3-70B-Euryale-v2.3
|
| 6 |
+
library_name: transformers
|
| 7 |
+
tags:
|
| 8 |
+
- mergekit
|
| 9 |
+
- merge
|
| 10 |
+
|
| 11 |
+
---
|
| 12 |
+
# output
|
| 13 |
+
|
| 14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 15 |
+
|
| 16 |
+
## Merge Details
|
| 17 |
+
### Merge Method
|
| 18 |
+
|
| 19 |
+
This model was merged using the Passthrough merge method.
|
| 20 |
+
|
| 21 |
+
### Models Merged
|
| 22 |
+
|
| 23 |
+
The following models were included in the merge:
|
| 24 |
+
* [TheDrummer/Anubis-70B-v1.1](https://huggingface.co/TheDrummer/Anubis-70B-v1.1)
|
| 25 |
+
* [sophosympatheia/Strawberrylemonade-L3-70B-v1.2](https://huggingface.co/sophosympatheia/Strawberrylemonade-L3-70B-v1.2)
|
| 26 |
+
* [Sao10K/L3.3-70B-Euryale-v2.3](https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3)
|
| 27 |
+
|
| 28 |
+
### Configuration
|
| 29 |
+
|
| 30 |
+
The following YAML configuration was used to produce this model:
|
| 31 |
+
|
| 32 |
+
```yaml
|
| 33 |
+
slices:
|
| 34 |
+
- sources:
|
| 35 |
+
- model: TheDrummer/Anubis-70B-v1.1
|
| 36 |
+
layer_range: [0, 40]
|
| 37 |
+
- sources:
|
| 38 |
+
- model: Sao10K/L3.3-70B-Euryale-v2.3
|
| 39 |
+
layer_range: [20, 60]
|
| 40 |
+
- sources:
|
| 41 |
+
- model: sophosympatheia/Strawberrylemonade-L3-70B-v1.2
|
| 42 |
+
layer_range: [40, 80]
|
| 43 |
+
merge_method: passthrough
|
| 44 |
+
dtype: bfloat16
|
| 45 |
+
|
| 46 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 8192,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 28672,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 64,
|
| 19 |
+
"num_hidden_layers": 120,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 128004,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"factor": 8.0,
|
| 26 |
+
"high_freq_factor": 4.0,
|
| 27 |
+
"low_freq_factor": 1.0,
|
| 28 |
+
"original_max_position_embeddings": 8192,
|
| 29 |
+
"rope_type": "llama3"
|
| 30 |
+
},
|
| 31 |
+
"rope_theta": 500000.0,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"transformers_version": "4.57.0",
|
| 34 |
+
"unsloth_fixed": true,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 128256
|
| 37 |
+
}
|
mergekit_config.yml
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
slices:
|
| 2 |
+
- sources:
|
| 3 |
+
- model: TheDrummer/Anubis-70B-v1.1
|
| 4 |
+
layer_range: [0, 40]
|
| 5 |
+
- sources:
|
| 6 |
+
- model: Sao10K/L3.3-70B-Euryale-v2.3
|
| 7 |
+
layer_range: [20, 60]
|
| 8 |
+
- sources:
|
| 9 |
+
- model: sophosympatheia/Strawberrylemonade-L3-70B-v1.2
|
| 10 |
+
layer_range: [40, 80]
|
| 11 |
+
merge_method: passthrough
|
| 12 |
+
dtype: bfloat16
|
model-00001-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ebd24b51850daef8786889f769c1ec6d83e48561c4effe3c41e68eab2c84ca8
|
| 3 |
+
size 4672471504
|
model-00002-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:722cb30ea86be5238879d926294fbc81c5dee53f8d1ec52b41f9ac8db493b0c2
|
| 3 |
+
size 4664167400
|
model-00003-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60496f8a1be7a4a524b59936f56fc3d2a81811aa994f43fb149b9c27484a0b53
|
| 3 |
+
size 4982917904
|
model-00004-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7855e7bfce3185d2e0c373ca57329b66933359035cefaee7fda77b82d2d3bc72
|
| 3 |
+
size 4999711736
|
model-00005-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b47aa13a535f1c400fe41545d7a8e7b1da266a8d22e91ff1728aaf44001e0574
|
| 3 |
+
size 4647373576
|
model-00006-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4106599ef462ffc04c84989762f4e13c8418e705ef0d1a2d4c46aa5bd84dffb
|
| 3 |
+
size 4831922696
|
model-00007-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f22532cc639188389c27129d7d52ff770744cdad7e2dec5100d210ecc45604d
|
| 3 |
+
size 4966190760
|
model-00008-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e72573653ee83284b7f85fb201fe1487dcd429da523f68875a5582bbbc7ab4
|
| 3 |
+
size 4831906224
|
model-00009-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f3a0ffca40649ec716fddc83cba02b35fab368c14b3d1a1478ef87321dac281
|
| 3 |
+
size 4966190768
|
model-00010-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34af340b125907ad6b91dca167206b33f72c5e95b7ed6b49c389486f61347fb1
|
| 3 |
+
size 4831906224
|
model-00011-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab53d1ae80d693b5e2ecd1e0ae7dab54280749a5f9a5f6c42555a942ea7e49d9
|
| 3 |
+
size 4999711736
|
model-00012-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfe13a03c3a92c0da563735da277971ff8ab9ddbafb4a765844ac153458f8ef8
|
| 3 |
+
size 4798385256
|
model-00013-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:717372fe7004f63d0dd3056adef79b6557e3683d0d82d0cd3c4923c7837aeabb
|
| 3 |
+
size 4664167408
|
model-00014-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cea30dd474f5f6d8584616df846829d38e7b2507d83f753b18c2bd84b9ce75a7
|
| 3 |
+
size 4831906224
|
model-00015-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f32d370cc615abe2703a3be64429e7d84b8a6c648ff21106c71b20bd48c73d5
|
| 3 |
+
size 4966190768
|
model-00016-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7628fec23465c807d97f3e9709a55d0d2b253be22aecc6c087ed05a0599c919
|
| 3 |
+
size 4831906224
|
model-00017-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c495b8d3b99f6705a1233bb2f748c8f0dba2054796bbdae4c1d689975276d6c
|
| 3 |
+
size 4999711736
|
model-00018-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff90a4988f5bae2e1296c713c13765396c8b9fc94e49b83631a9fec9823c0dd6
|
| 3 |
+
size 4798385256
|
model-00019-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d05e280abd66fc39d33cd779ae3a237be862668498c523f3c22f8a21a7ffb046
|
| 3 |
+
size 4831906216
|
model-00020-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d561f7a847e72345efbb10552938c8798d26bea86cd05e9060cac69da180bdd6
|
| 3 |
+
size 4966174264
|
model-00021-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d575f3d8e79a72a64055894bc0201b13b87d190a1344473e524a68e3122bdf5b
|
| 3 |
+
size 4664183904
|
model-00022-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e2d242a6d2a80fcf8e603f94ec8a9fe4fbd176c01b1416daa160899994d0caf
|
| 3 |
+
size 4831906224
|
model-00023-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69a1e8b7d99e41f7da0ee3432714a0756cc7db4cc00945d573b87068785b5a2
|
| 3 |
+
size 4999711736
|
model-00024-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a27b655d5e2b9867af0ae87f5e18c2516ccb370b9ebc97159af80e475061f234
|
| 3 |
+
size 4798385256
|
model-00025-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0c4033450d115bdcce6be5aa7beae826af8d9b7f74e150801b6d5ec61b93b1a
|
| 3 |
+
size 4831906216
|
model-00026-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2439802e6a81fed0f4231a8c7c0dfae78a960485165e1551a5d78ff1fe82fdd
|
| 3 |
+
size 4966190760
|
model-00027-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9a4c9408ceb182041520b5c5eddb8b47c955b01c2ceededadc40d941448d404
|
| 3 |
+
size 4831906224
|
model-00028-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a66c560bd5f6b7474359a11df66dd8d633e37564a1578e68878f2c576c733c0f
|
| 3 |
+
size 4664167400
|
model-00029-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d7c59cd7cf9ebeb9d6cae87f3f89cf97bea3e6c05f22aaab24f5c0b57f07a48
|
| 3 |
+
size 4999711736
|
model-00030-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988215ad1c43b1cc2859039cc347b41d2c401f02f12b9366e7e3e2e34357be60
|
| 3 |
+
size 4798385256
|
model-00031-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f35a249becb8b5ad577f72f907f35eb70c2c382b51638ac359c9a167c4d16b25
|
| 3 |
+
size 4831906216
|
model-00032-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70077beb9c8affc87f513400646968e316ae700fd730dc4affb30617a781de40
|
| 3 |
+
size 4966190760
|
model-00033-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfe7d0ed8c492f159eb18aa8b719eb7c3a4fae6a8aa158f37f458c8b1c2951fc
|
| 3 |
+
size 4831906224
|
model-00034-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad09dd361cb1fb5aaa791610698d5fcdf5306d2af70e072bb85280efc5fbe339
|
| 3 |
+
size 4966190768
|
model-00035-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8855b018109c37287f2e166988df07fa107e14a656e426f7a2e338226b74540
|
| 3 |
+
size 4982901392
|
model-00036-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c564276933795d6de29011e7a29c76ec6a2c37ee3da9eca280f33b61df54b230
|
| 3 |
+
size 4999711752
|
model-00037-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1ebf714f75a8c354ba849de140b0d88b4d1f4b9e3c5770ba983a9785fbaae34
|
| 3 |
+
size 4647373600
|
model-00038-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66395cd255533c8609e22cc75581f81a69d1e33c518a6df5ee016d61cf4a848d
|
| 3 |
+
size 4664167432
|
model-00039-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced18b287cbd6d3b645b237b9e5376ecb3d9afd3d6c6e5f6a33933a2757487b4
|
| 3 |
+
size 4664167424
|
model-00040-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa86213b000531533af2d41d207e92a43fc27b47b1678ea51e8548cdde87815f
|
| 3 |
+
size 4982917928
|
model-00041-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b6fa7bb7a300e76d1fe93c4f4a7a6d1c56b14c94ba45e8c4ddaa1de1efe8253
|
| 3 |
+
size 4999711760
|
model-00042-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ec45162da7fb1a9fb67886c48c31948e2999875002843d9fb7e97ebbf793d17
|
| 3 |
+
size 4647373600
|
model-00043-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:727dc24bba077707a689d5069bee83c61de49cc9725463f6ddbbcf61b1dc7104
|
| 3 |
+
size 4664167416
|
model-00044-of-00044.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cf6b2e74b318b7878f0d91031915697c9dbbe54d1880519c3e8b2e91050ac32
|
| 3 |
+
size 1241547688
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00044.safetensors", "model.embed_tokens.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.safetensors"}}
|