Text Generation
Transformers
PyTorch
Safetensors
Arabic
English
llama
conversational
text-generation-inference
Inference Endpoints

Upload folder using huggingface_hub

#1
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/import/ml-sc-scratch6/bol/thai_70b_dpo/sft_run/out_ar_2/step_659/config.json",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 4096,
15
+ "model_name": "",
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "return_dict": false,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.31.0",
29
+ "use_cache": true,
30
+ "vocab_size": 57344
31
+ }
pytorch_model-01-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3629d019e51c99d7c84e4e14bb41b36f262be23b19562711717774fde978a19a
3
+ size 3892352979
pytorch_model-02-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2e3003385b2662b42931a927c4fe0ed8b82d939813ad4a650ef55cd0ec4158
3
+ size 4194411495
pytorch_model-03-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c44dd6a67274ecd7b3a69a1e5630eb8a8f58bc31e8c9b688614b8df81cd123
3
+ size 3892386649
pytorch_model-04-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ecd16f5c2a9b49dcf0393a2f8b9339b88a525c4caa159216d1a88d52fc84d1e
3
+ size 3892386649
pytorch_model-05-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe32d669f31c0cf58d43d5f80b9bab2625c48c120c46dcde2f47edbd35c714f8
3
+ size 4194411495
pytorch_model-06-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6606c79b5732aec107007ef6f4a08135d6660b8e7b0647544363715bc385c16d
3
+ size 3892386649
pytorch_model-07-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b6edc176b4b917752e95ade836bb81e368e09d961b36a534b1a0cdf74aeb2c
3
+ size 3892386649
pytorch_model-08-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484ee17347dd71f22ffbae2b78eaa751a451bc5dfc3b2a87a474ab7abc422b13
3
+ size 4194411495
pytorch_model-09-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93833efc64d7da857f86762ecb76ab7ece0e23cdcf4101d20aa0b92460da43d1
3
+ size 3892386649
pytorch_model-10-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d515f3aac587c4fd65e243fe6f8e52a3bf5c03a57b35ad70eaa39078cfccc4
3
+ size 3892386649
pytorch_model-11-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d1255c08793301adf13a2e3bb7ff23669d2d26fe88309f8c33cc6ccc71e5a4
3
+ size 4194411589
pytorch_model-12-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0a056703d2b453acb4311392b9f2615841c97adf27bd8f82623abd94cd839d
3
+ size 3892386672
pytorch_model-13-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf4f6dd2951636bf1ff5682c1f2e42ecc773361c2eecc249d547d1f0b3ccafd
3
+ size 3892386672
pytorch_model-14-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f3531595a330fd81825c27059544bf4f061b0f3c58871e1964f2ceb93c6575
3
+ size 4194411589
pytorch_model-15-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afffd0617ea2ebdcf1cb8e7e686bf7d2b02c1b017c3141cefeb5274bef2c4b70
3
+ size 3892386672
pytorch_model-16-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84cdcf40f460a98f1f7e974289a7bbc79667812517607327dc14a0160806a987
3
+ size 3892386672
pytorch_model-17-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab141f6e34f2f3b9fded5e4e6dac6b3814380ec257137c6b27f2cfd2573453a
3
+ size 4194411589
pytorch_model-18-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4102124b5c98ac01d1dc006abf62265e82f584126f51c746a287924c6253614b
3
+ size 3892386672
pytorch_model-19-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc8053d708d182c19acf132206eadf0bc2fe7d0db0736b45c8d4911d5fe9ee3
3
+ size 3892386672
pytorch_model-20-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6264337f39c79176820777bd814f1070dc1140f7aac95bc591731d85130e4891
3
+ size 4194411589
pytorch_model-21-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0018a18e3897be09ed9530bc3e477f0779067fb34b1ac9d521312aa5eab976d
3
+ size 3892386672
pytorch_model-22-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2935ce31d3df9e7afc993a2719233aceafa5c22a87ea4de6669e482e96330363
3
+ size 3892386672
pytorch_model-23-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca98f8c6db43d1329b9c20880f4490b23bfd97c5167628842765ed0e2251c63f
3
+ size 4194411589
pytorch_model-24-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce04e41f38c1c68d4aa2a17fb245da06271245493890c871683bfe485d18c749
3
+ size 3892386672
pytorch_model-25-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514fb71d8e11af892d1b10f1bf51e8f7c0862001c69e64c84cf0d082513c09f9
3
+ size 3892386672
pytorch_model-26-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8033df8bebbdc14743decfbafe3c14959c05384b275dd5353efcea82b1406b6
3
+ size 4194411589
pytorch_model-27-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa85341ab8dbc27fdf2d7133cdd1c005f7f05c8ee2f1738dc4a2716fc3f97122
3
+ size 3892386672
pytorch_model-28-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44eb8584a9a8cba383ba0f47811eab8d009fb77b6d827f939b4f1ac710e93e81
3
+ size 3892386672
pytorch_model-29-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d794d66c50f7b0a5949cb7b1170fb7e6650951b48ae8ff9ec6e9961620410d7
3
+ size 4194411589
pytorch_model-30-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34671a37b74730ead716f5fba093c0bcd6dbde2d051cebe9eb0dddbc4afaaf8
3
+ size 3892386672
pytorch_model-31-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e164025de89149348be2e62eb097b7879985c5c57f6dcc435acd1a3c788b7a
3
+ size 3892386672
pytorch_model-32-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3dfc30564ca44e58d5507a0aa5ebd73a55bc63cf4698aeffd62defbe65b0b0
3
+ size 4194411589
pytorch_model-33-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad942e43dd05c5fec4803b43aeff7c643b1800011dbcae515616f33fb195d45f
3
+ size 3892386672
pytorch_model-34-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b770b233b3e40cb5b15abd94f009d19d3fc8a3e1a96d5aa9ad8cc9856858b86
3
+ size 3892386672
pytorch_model-35-of-35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:877028a9f3cd009ea6596172992c051d4f3ceb8af48119228380b1e6cca87dd1
3
+ size 3120649182
pytorch_model.bin.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {}, "weight_map": {"model.embed_tokens.weight": "pytorch_model-01-of-35.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-01-of-35.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-01-of-35.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-01-of-35.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-01-of-35.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-01-of-35.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-02-of-35.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-02-of-35.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-02-of-35.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-02-of-35.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-02-of-35.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-02-of-35.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-02-of-35.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-02-of-35.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-02-of-35.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-02-of-35.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-03-of-35.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-03-of-35.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-03-of-35.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-03-of-35.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-03-of-35.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-03-of-35.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-03-of-35.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-04-of-35.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-04-of-35.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-04-of-35.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-04-of-35.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-04-of-35.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-04-of-35.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-04-of-35.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-05-of-35.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-05-of-35.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-05-of-35.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-05-of-35.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-05-of-35.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-05-of-35.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-05-of-35.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-05-of-35.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-05-of-35.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-05-of-35.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-06-of-35.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-06-of-35.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-06-of-35.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-06-of-35.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-06-of-35.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-06-of-35.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-06-of-35.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-07-of-35.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-07-of-35.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-07-of-35.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-07-of-35.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-07-of-35.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-07-of-35.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-07-of-35.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-08-of-35.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-08-of-35.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-08-of-35.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-08-of-35.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-08-of-35.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-08-of-35.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-08-of-35.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-08-of-35.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-08-of-35.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-08-of-35.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-09-of-35.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-09-of-35.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-09-of-35.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-09-of-35.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-09-of-35.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-09-of-35.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-09-of-35.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-10-of-35.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-10-of-35.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-10-of-35.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-10-of-35.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-10-of-35.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-10-of-35.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-10-of-35.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-11-of-35.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-11-of-35.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-35.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-11-of-35.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-11-of-35.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-35.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-11-of-35.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-11-of-35.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-11-of-35.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-35.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-12-of-35.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-12-of-35.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-12-of-35.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-12-of-35.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-12-of-35.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-12-of-35.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-12-of-35.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-13-of-35.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-13-of-35.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-13-of-35.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-13-of-35.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-13-of-35.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-13-of-35.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-13-of-35.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-14-of-35.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-14-of-35.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-35.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-14-of-35.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-14-of-35.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-35.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-14-of-35.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-14-of-35.bin", "model.layers.32.self_attn.q_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.32.self_attn.k_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.32.self_attn.v_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.32.self_attn.o_proj.weight": "pytorch_model-14-of-35.bin", "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-35.bin", "model.layers.32.mlp.gate_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.32.mlp.up_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.32.mlp.down_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.32.input_layernorm.weight": "pytorch_model-15-of-35.bin", "model.layers.32.post_attention_layernorm.weight": "pytorch_model-15-of-35.bin", "model.layers.33.self_attn.q_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.self_attn.k_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.self_attn.v_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.self_attn.o_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-15-of-35.bin", "model.layers.33.mlp.gate_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.mlp.up_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.mlp.down_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.33.input_layernorm.weight": "pytorch_model-15-of-35.bin", "model.layers.33.post_attention_layernorm.weight": "pytorch_model-15-of-35.bin", "model.layers.34.self_attn.q_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.34.self_attn.k_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.34.self_attn.v_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.34.self_attn.o_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-15-of-35.bin", "model.layers.34.mlp.gate_proj.weight": "pytorch_model-15-of-35.bin", "model.layers.34.mlp.up_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.34.mlp.down_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.34.input_layernorm.weight": "pytorch_model-16-of-35.bin", "model.layers.34.post_attention_layernorm.weight": "pytorch_model-16-of-35.bin", "model.layers.35.self_attn.q_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.self_attn.k_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.self_attn.v_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.self_attn.o_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-16-of-35.bin", "model.layers.35.mlp.gate_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.mlp.up_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.mlp.down_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.35.input_layernorm.weight": "pytorch_model-16-of-35.bin", "model.layers.35.post_attention_layernorm.weight": "pytorch_model-16-of-35.bin", "model.layers.36.self_attn.q_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.36.self_attn.k_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.36.self_attn.v_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.36.self_attn.o_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-16-of-35.bin", "model.layers.36.mlp.gate_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.36.mlp.up_proj.weight": "pytorch_model-16-of-35.bin", "model.layers.36.mlp.down_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.36.input_layernorm.weight": "pytorch_model-17-of-35.bin", "model.layers.36.post_attention_layernorm.weight": "pytorch_model-17-of-35.bin", "model.layers.37.self_attn.q_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.self_attn.k_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.self_attn.v_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.self_attn.o_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-35.bin", "model.layers.37.mlp.gate_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.mlp.up_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.mlp.down_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.37.input_layernorm.weight": "pytorch_model-17-of-35.bin", "model.layers.37.post_attention_layernorm.weight": "pytorch_model-17-of-35.bin", "model.layers.38.self_attn.q_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.self_attn.k_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.self_attn.v_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.self_attn.o_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-35.bin", "model.layers.38.mlp.gate_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.mlp.up_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.mlp.down_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.38.input_layernorm.weight": "pytorch_model-17-of-35.bin", "model.layers.38.post_attention_layernorm.weight": "pytorch_model-17-of-35.bin", "model.layers.39.self_attn.q_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.39.self_attn.k_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.39.self_attn.v_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.39.self_attn.o_proj.weight": "pytorch_model-17-of-35.bin", "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-35.bin", "model.layers.39.mlp.gate_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.39.mlp.up_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.39.mlp.down_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.39.input_layernorm.weight": "pytorch_model-18-of-35.bin", "model.layers.39.post_attention_layernorm.weight": "pytorch_model-18-of-35.bin", "model.layers.40.self_attn.q_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.self_attn.k_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.self_attn.v_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.self_attn.o_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-18-of-35.bin", "model.layers.40.mlp.gate_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.mlp.up_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.mlp.down_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.40.input_layernorm.weight": "pytorch_model-18-of-35.bin", "model.layers.40.post_attention_layernorm.weight": "pytorch_model-18-of-35.bin", "model.layers.41.self_attn.q_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.41.self_attn.k_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.41.self_attn.v_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.41.self_attn.o_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-18-of-35.bin", "model.layers.41.mlp.gate_proj.weight": "pytorch_model-18-of-35.bin", "model.layers.41.mlp.up_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.41.mlp.down_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.41.input_layernorm.weight": "pytorch_model-19-of-35.bin", "model.layers.41.post_attention_layernorm.weight": "pytorch_model-19-of-35.bin", "model.layers.42.self_attn.q_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.self_attn.k_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.self_attn.v_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.self_attn.o_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-19-of-35.bin", "model.layers.42.mlp.gate_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.mlp.up_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.mlp.down_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.42.input_layernorm.weight": "pytorch_model-19-of-35.bin", "model.layers.42.post_attention_layernorm.weight": "pytorch_model-19-of-35.bin", "model.layers.43.self_attn.q_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.43.self_attn.k_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.43.self_attn.v_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.43.self_attn.o_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-19-of-35.bin", "model.layers.43.mlp.gate_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.43.mlp.up_proj.weight": "pytorch_model-19-of-35.bin", "model.layers.43.mlp.down_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.43.input_layernorm.weight": "pytorch_model-20-of-35.bin", "model.layers.43.post_attention_layernorm.weight": "pytorch_model-20-of-35.bin", "model.layers.44.self_attn.q_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.self_attn.k_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.self_attn.v_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.self_attn.o_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-35.bin", "model.layers.44.mlp.gate_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.mlp.up_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.mlp.down_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.44.input_layernorm.weight": "pytorch_model-20-of-35.bin", "model.layers.44.post_attention_layernorm.weight": "pytorch_model-20-of-35.bin", "model.layers.45.self_attn.q_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.self_attn.k_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.self_attn.v_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.self_attn.o_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-35.bin", "model.layers.45.mlp.gate_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.mlp.up_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.mlp.down_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.45.input_layernorm.weight": "pytorch_model-20-of-35.bin", "model.layers.45.post_attention_layernorm.weight": "pytorch_model-20-of-35.bin", "model.layers.46.self_attn.q_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.46.self_attn.k_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.46.self_attn.v_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.46.self_attn.o_proj.weight": "pytorch_model-20-of-35.bin", "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-35.bin", "model.layers.46.mlp.gate_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.46.mlp.up_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.46.mlp.down_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.46.input_layernorm.weight": "pytorch_model-21-of-35.bin", "model.layers.46.post_attention_layernorm.weight": "pytorch_model-21-of-35.bin", "model.layers.47.self_attn.q_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.self_attn.k_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.self_attn.v_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.self_attn.o_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-21-of-35.bin", "model.layers.47.mlp.gate_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.mlp.up_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.mlp.down_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.47.input_layernorm.weight": "pytorch_model-21-of-35.bin", "model.layers.47.post_attention_layernorm.weight": "pytorch_model-21-of-35.bin", "model.layers.48.self_attn.q_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.48.self_attn.k_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.48.self_attn.v_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.48.self_attn.o_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-21-of-35.bin", "model.layers.48.mlp.gate_proj.weight": "pytorch_model-21-of-35.bin", "model.layers.48.mlp.up_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.48.mlp.down_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.48.input_layernorm.weight": "pytorch_model-22-of-35.bin", "model.layers.48.post_attention_layernorm.weight": "pytorch_model-22-of-35.bin", "model.layers.49.self_attn.q_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.self_attn.k_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.self_attn.v_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.self_attn.o_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-22-of-35.bin", "model.layers.49.mlp.gate_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.mlp.up_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.mlp.down_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.49.input_layernorm.weight": "pytorch_model-22-of-35.bin", "model.layers.49.post_attention_layernorm.weight": "pytorch_model-22-of-35.bin", "model.layers.50.self_attn.q_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.50.self_attn.k_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.50.self_attn.v_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.50.self_attn.o_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-22-of-35.bin", "model.layers.50.mlp.gate_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.50.mlp.up_proj.weight": "pytorch_model-22-of-35.bin", "model.layers.50.mlp.down_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.50.input_layernorm.weight": "pytorch_model-23-of-35.bin", "model.layers.50.post_attention_layernorm.weight": "pytorch_model-23-of-35.bin", "model.layers.51.self_attn.q_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.self_attn.k_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.self_attn.v_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.self_attn.o_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-35.bin", "model.layers.51.mlp.gate_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.mlp.up_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.mlp.down_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.51.input_layernorm.weight": "pytorch_model-23-of-35.bin", "model.layers.51.post_attention_layernorm.weight": "pytorch_model-23-of-35.bin", "model.layers.52.self_attn.q_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.self_attn.k_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.self_attn.v_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.self_attn.o_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-35.bin", "model.layers.52.mlp.gate_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.mlp.up_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.mlp.down_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.52.input_layernorm.weight": "pytorch_model-23-of-35.bin", "model.layers.52.post_attention_layernorm.weight": "pytorch_model-23-of-35.bin", "model.layers.53.self_attn.q_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.53.self_attn.k_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.53.self_attn.v_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.53.self_attn.o_proj.weight": "pytorch_model-23-of-35.bin", "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-35.bin", "model.layers.53.mlp.gate_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.53.mlp.up_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.53.mlp.down_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.53.input_layernorm.weight": "pytorch_model-24-of-35.bin", "model.layers.53.post_attention_layernorm.weight": "pytorch_model-24-of-35.bin", "model.layers.54.self_attn.q_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.self_attn.k_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.self_attn.v_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.self_attn.o_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-24-of-35.bin", "model.layers.54.mlp.gate_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.mlp.up_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.mlp.down_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.54.input_layernorm.weight": "pytorch_model-24-of-35.bin", "model.layers.54.post_attention_layernorm.weight": "pytorch_model-24-of-35.bin", "model.layers.55.self_attn.q_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.55.self_attn.k_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.55.self_attn.v_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.55.self_attn.o_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-24-of-35.bin", "model.layers.55.mlp.gate_proj.weight": "pytorch_model-24-of-35.bin", "model.layers.55.mlp.up_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.55.mlp.down_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.55.input_layernorm.weight": "pytorch_model-25-of-35.bin", "model.layers.55.post_attention_layernorm.weight": "pytorch_model-25-of-35.bin", "model.layers.56.self_attn.q_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.self_attn.k_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.self_attn.v_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.self_attn.o_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-25-of-35.bin", "model.layers.56.mlp.gate_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.mlp.up_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.mlp.down_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.56.input_layernorm.weight": "pytorch_model-25-of-35.bin", "model.layers.56.post_attention_layernorm.weight": "pytorch_model-25-of-35.bin", "model.layers.57.self_attn.q_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.57.self_attn.k_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.57.self_attn.v_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.57.self_attn.o_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-25-of-35.bin", "model.layers.57.mlp.gate_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.57.mlp.up_proj.weight": "pytorch_model-25-of-35.bin", "model.layers.57.mlp.down_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.57.input_layernorm.weight": "pytorch_model-26-of-35.bin", "model.layers.57.post_attention_layernorm.weight": "pytorch_model-26-of-35.bin", "model.layers.58.self_attn.q_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.self_attn.k_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.self_attn.v_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.self_attn.o_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-35.bin", "model.layers.58.mlp.gate_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.mlp.up_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.mlp.down_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.58.input_layernorm.weight": "pytorch_model-26-of-35.bin", "model.layers.58.post_attention_layernorm.weight": "pytorch_model-26-of-35.bin", "model.layers.59.self_attn.q_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.self_attn.k_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.self_attn.v_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.self_attn.o_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-35.bin", "model.layers.59.mlp.gate_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.mlp.up_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.mlp.down_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.59.input_layernorm.weight": "pytorch_model-26-of-35.bin", "model.layers.59.post_attention_layernorm.weight": "pytorch_model-26-of-35.bin", "model.layers.60.self_attn.q_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.60.self_attn.k_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.60.self_attn.v_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.60.self_attn.o_proj.weight": "pytorch_model-26-of-35.bin", "model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-35.bin", "model.layers.60.mlp.gate_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.60.mlp.up_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.60.mlp.down_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.60.input_layernorm.weight": "pytorch_model-27-of-35.bin", "model.layers.60.post_attention_layernorm.weight": "pytorch_model-27-of-35.bin", "model.layers.61.self_attn.q_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.self_attn.k_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.self_attn.v_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.self_attn.o_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-27-of-35.bin", "model.layers.61.mlp.gate_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.mlp.up_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.mlp.down_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.61.input_layernorm.weight": "pytorch_model-27-of-35.bin", "model.layers.61.post_attention_layernorm.weight": "pytorch_model-27-of-35.bin", "model.layers.62.self_attn.q_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.62.self_attn.k_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.62.self_attn.v_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.62.self_attn.o_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-27-of-35.bin", "model.layers.62.mlp.gate_proj.weight": "pytorch_model-27-of-35.bin", "model.layers.62.mlp.up_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.62.mlp.down_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.62.input_layernorm.weight": "pytorch_model-28-of-35.bin", "model.layers.62.post_attention_layernorm.weight": "pytorch_model-28-of-35.bin", "model.layers.63.self_attn.q_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.self_attn.k_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.self_attn.v_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.self_attn.o_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-28-of-35.bin", "model.layers.63.mlp.gate_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.mlp.up_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.mlp.down_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.63.input_layernorm.weight": "pytorch_model-28-of-35.bin", "model.layers.63.post_attention_layernorm.weight": "pytorch_model-28-of-35.bin", "model.layers.64.self_attn.q_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.64.self_attn.k_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.64.self_attn.v_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.64.self_attn.o_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-28-of-35.bin", "model.layers.64.mlp.gate_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.64.mlp.up_proj.weight": "pytorch_model-28-of-35.bin", "model.layers.64.mlp.down_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.64.input_layernorm.weight": "pytorch_model-29-of-35.bin", "model.layers.64.post_attention_layernorm.weight": "pytorch_model-29-of-35.bin", "model.layers.65.self_attn.q_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.self_attn.k_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.self_attn.v_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.self_attn.o_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-35.bin", "model.layers.65.mlp.gate_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.mlp.up_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.mlp.down_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.65.input_layernorm.weight": "pytorch_model-29-of-35.bin", "model.layers.65.post_attention_layernorm.weight": "pytorch_model-29-of-35.bin", "model.layers.66.self_attn.q_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.self_attn.k_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.self_attn.v_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.self_attn.o_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-35.bin", "model.layers.66.mlp.gate_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.mlp.up_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.mlp.down_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.66.input_layernorm.weight": "pytorch_model-29-of-35.bin", "model.layers.66.post_attention_layernorm.weight": "pytorch_model-29-of-35.bin", "model.layers.67.self_attn.q_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.67.self_attn.k_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.67.self_attn.v_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.67.self_attn.o_proj.weight": "pytorch_model-29-of-35.bin", "model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-35.bin", "model.layers.67.mlp.gate_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.67.mlp.up_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.67.mlp.down_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.67.input_layernorm.weight": "pytorch_model-30-of-35.bin", "model.layers.67.post_attention_layernorm.weight": "pytorch_model-30-of-35.bin", "model.layers.68.self_attn.q_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.self_attn.k_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.self_attn.v_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.self_attn.o_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-30-of-35.bin", "model.layers.68.mlp.gate_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.mlp.up_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.mlp.down_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.68.input_layernorm.weight": "pytorch_model-30-of-35.bin", "model.layers.68.post_attention_layernorm.weight": "pytorch_model-30-of-35.bin", "model.layers.69.self_attn.q_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.69.self_attn.k_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.69.self_attn.v_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.69.self_attn.o_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-30-of-35.bin", "model.layers.69.mlp.gate_proj.weight": "pytorch_model-30-of-35.bin", "model.layers.69.mlp.up_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.69.mlp.down_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.69.input_layernorm.weight": "pytorch_model-31-of-35.bin", "model.layers.69.post_attention_layernorm.weight": "pytorch_model-31-of-35.bin", "model.layers.70.self_attn.q_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.self_attn.k_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.self_attn.v_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.self_attn.o_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-31-of-35.bin", "model.layers.70.mlp.gate_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.mlp.up_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.mlp.down_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.70.input_layernorm.weight": "pytorch_model-31-of-35.bin", "model.layers.70.post_attention_layernorm.weight": "pytorch_model-31-of-35.bin", "model.layers.71.self_attn.q_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.71.self_attn.k_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.71.self_attn.v_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.71.self_attn.o_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-31-of-35.bin", "model.layers.71.mlp.gate_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.71.mlp.up_proj.weight": "pytorch_model-31-of-35.bin", "model.layers.71.mlp.down_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.71.input_layernorm.weight": "pytorch_model-32-of-35.bin", "model.layers.71.post_attention_layernorm.weight": "pytorch_model-32-of-35.bin", "model.layers.72.self_attn.q_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.self_attn.k_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.self_attn.v_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.self_attn.o_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-35.bin", "model.layers.72.mlp.gate_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.mlp.up_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.mlp.down_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.72.input_layernorm.weight": "pytorch_model-32-of-35.bin", "model.layers.72.post_attention_layernorm.weight": "pytorch_model-32-of-35.bin", "model.layers.73.self_attn.q_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.self_attn.k_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.self_attn.v_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.self_attn.o_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-35.bin", "model.layers.73.mlp.gate_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.mlp.up_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.mlp.down_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.73.input_layernorm.weight": "pytorch_model-32-of-35.bin", "model.layers.73.post_attention_layernorm.weight": "pytorch_model-32-of-35.bin", "model.layers.74.self_attn.q_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.74.self_attn.k_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.74.self_attn.v_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.74.self_attn.o_proj.weight": "pytorch_model-32-of-35.bin", "model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-35.bin", "model.layers.74.mlp.gate_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.74.mlp.up_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.74.mlp.down_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.74.input_layernorm.weight": "pytorch_model-33-of-35.bin", "model.layers.74.post_attention_layernorm.weight": "pytorch_model-33-of-35.bin", "model.layers.75.self_attn.q_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.self_attn.k_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.self_attn.v_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.self_attn.o_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-33-of-35.bin", "model.layers.75.mlp.gate_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.mlp.up_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.mlp.down_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.75.input_layernorm.weight": "pytorch_model-33-of-35.bin", "model.layers.75.post_attention_layernorm.weight": "pytorch_model-33-of-35.bin", "model.layers.76.self_attn.q_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.76.self_attn.k_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.76.self_attn.v_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.76.self_attn.o_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-33-of-35.bin", "model.layers.76.mlp.gate_proj.weight": "pytorch_model-33-of-35.bin", "model.layers.76.mlp.up_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.76.mlp.down_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.76.input_layernorm.weight": "pytorch_model-34-of-35.bin", "model.layers.76.post_attention_layernorm.weight": "pytorch_model-34-of-35.bin", "model.layers.77.self_attn.q_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.self_attn.k_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.self_attn.v_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.self_attn.o_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-34-of-35.bin", "model.layers.77.mlp.gate_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.mlp.up_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.mlp.down_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.77.input_layernorm.weight": "pytorch_model-34-of-35.bin", "model.layers.77.post_attention_layernorm.weight": "pytorch_model-34-of-35.bin", "model.layers.78.self_attn.q_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.78.self_attn.k_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.78.self_attn.v_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.78.self_attn.o_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-34-of-35.bin", "model.layers.78.mlp.gate_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.78.mlp.up_proj.weight": "pytorch_model-34-of-35.bin", "model.layers.78.mlp.down_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.78.input_layernorm.weight": "pytorch_model-35-of-35.bin", "model.layers.78.post_attention_layernorm.weight": "pytorch_model-35-of-35.bin", "model.layers.79.self_attn.q_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.self_attn.k_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.self_attn.v_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.self_attn.o_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-35-of-35.bin", "model.layers.79.mlp.gate_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.mlp.up_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.mlp.down_proj.weight": "pytorch_model-35-of-35.bin", "model.layers.79.input_layernorm.weight": "pytorch_model-35-of-35.bin", "model.layers.79.post_attention_layernorm.weight": "pytorch_model-35-of-35.bin", "model.norm.weight": "pytorch_model-35-of-35.bin", "lm_head.weight": "pytorch_model-35-of-35.bin"}}
pytorch_model.bin.sambatensor_index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model.embed_tokens.weight": "llamaforcausallm__model__embed_tokens__weight", "model.layers.0.self_attn.q_proj.weight": "llamaforcausallm__model__layers__0__self_attn__q_proj__weight", "model.layers.0.self_attn.k_proj.weight": "llamaforcausallm__model__layers__0__self_attn__k_proj__weight", "model.layers.0.self_attn.v_proj.weight": "llamaforcausallm__model__layers__0__self_attn__v_proj__weight", "model.layers.0.self_attn.o_proj.weight": "llamaforcausallm__model__layers__0__self_attn__o_proj__weight", "model.layers.0.mlp.gate_proj.weight": "llamaforcausallm__model__layers__0__mlp__gate_proj__weight", "model.layers.0.mlp.up_proj.weight": "llamaforcausallm__model__layers__0__mlp__up_proj__weight", "model.layers.0.mlp.down_proj.weight": "llamaforcausallm__model__layers__0__mlp__down_proj__weight", "model.layers.0.input_layernorm.weight": "llamaforcausallm__model__layers__0__input_layernorm__weight", "model.layers.0.post_attention_layernorm.weight": "llamaforcausallm__model__layers__0__post_attention_layernorm__weight", "model.layers.1.self_attn.q_proj.weight": "llamaforcausallm__model__layers__1__self_attn__q_proj__weight", "model.layers.1.self_attn.k_proj.weight": "llamaforcausallm__model__layers__1__self_attn__k_proj__weight", "model.layers.1.self_attn.v_proj.weight": "llamaforcausallm__model__layers__1__self_attn__v_proj__weight", "model.layers.1.self_attn.o_proj.weight": "llamaforcausallm__model__layers__1__self_attn__o_proj__weight", "model.layers.1.mlp.gate_proj.weight": "llamaforcausallm__model__layers__1__mlp__gate_proj__weight", "model.layers.1.mlp.up_proj.weight": "llamaforcausallm__model__layers__1__mlp__up_proj__weight", "model.layers.1.mlp.down_proj.weight": "llamaforcausallm__model__layers__1__mlp__down_proj__weight", "model.layers.1.input_layernorm.weight": "llamaforcausallm__model__layers__1__input_layernorm__weight", "model.layers.1.post_attention_layernorm.weight": "llamaforcausallm__model__layers__1__post_attention_layernorm__weight", "model.layers.2.self_attn.q_proj.weight": "llamaforcausallm__model__layers__2__self_attn__q_proj__weight", "model.layers.2.self_attn.k_proj.weight": "llamaforcausallm__model__layers__2__self_attn__k_proj__weight", "model.layers.2.self_attn.v_proj.weight": "llamaforcausallm__model__layers__2__self_attn__v_proj__weight", "model.layers.2.self_attn.o_proj.weight": "llamaforcausallm__model__layers__2__self_attn__o_proj__weight", "model.layers.2.mlp.gate_proj.weight": "llamaforcausallm__model__layers__2__mlp__gate_proj__weight", "model.layers.2.mlp.up_proj.weight": "llamaforcausallm__model__layers__2__mlp__up_proj__weight", "model.layers.2.mlp.down_proj.weight": "llamaforcausallm__model__layers__2__mlp__down_proj__weight", "model.layers.2.input_layernorm.weight": "llamaforcausallm__model__layers__2__input_layernorm__weight", "model.layers.2.post_attention_layernorm.weight": "llamaforcausallm__model__layers__2__post_attention_layernorm__weight", "model.layers.3.self_attn.q_proj.weight": "llamaforcausallm__model__layers__3__self_attn__q_proj__weight", "model.layers.3.self_attn.k_proj.weight": "llamaforcausallm__model__layers__3__self_attn__k_proj__weight", "model.layers.3.self_attn.v_proj.weight": "llamaforcausallm__model__layers__3__self_attn__v_proj__weight", "model.layers.3.self_attn.o_proj.weight": "llamaforcausallm__model__layers__3__self_attn__o_proj__weight", "model.layers.3.mlp.gate_proj.weight": "llamaforcausallm__model__layers__3__mlp__gate_proj__weight", "model.layers.3.mlp.up_proj.weight": "llamaforcausallm__model__layers__3__mlp__up_proj__weight", "model.layers.3.mlp.down_proj.weight": "llamaforcausallm__model__layers__3__mlp__down_proj__weight", "model.layers.3.input_layernorm.weight": "llamaforcausallm__model__layers__3__input_layernorm__weight", "model.layers.3.post_attention_layernorm.weight": "llamaforcausallm__model__layers__3__post_attention_layernorm__weight", "model.layers.4.self_attn.q_proj.weight": "llamaforcausallm__model__layers__4__self_attn__q_proj__weight", "model.layers.4.self_attn.k_proj.weight": "llamaforcausallm__model__layers__4__self_attn__k_proj__weight", "model.layers.4.self_attn.v_proj.weight": "llamaforcausallm__model__layers__4__self_attn__v_proj__weight", "model.layers.4.self_attn.o_proj.weight": "llamaforcausallm__model__layers__4__self_attn__o_proj__weight", "model.layers.4.mlp.gate_proj.weight": "llamaforcausallm__model__layers__4__mlp__gate_proj__weight", "model.layers.4.mlp.up_proj.weight": "llamaforcausallm__model__layers__4__mlp__up_proj__weight", "model.layers.4.mlp.down_proj.weight": "llamaforcausallm__model__layers__4__mlp__down_proj__weight", "model.layers.4.input_layernorm.weight": "llamaforcausallm__model__layers__4__input_layernorm__weight", "model.layers.4.post_attention_layernorm.weight": "llamaforcausallm__model__layers__4__post_attention_layernorm__weight", "model.layers.5.self_attn.q_proj.weight": "llamaforcausallm__model__layers__5__self_attn__q_proj__weight", "model.layers.5.self_attn.k_proj.weight": "llamaforcausallm__model__layers__5__self_attn__k_proj__weight", "model.layers.5.self_attn.v_proj.weight": "llamaforcausallm__model__layers__5__self_attn__v_proj__weight", "model.layers.5.self_attn.o_proj.weight": "llamaforcausallm__model__layers__5__self_attn__o_proj__weight", "model.layers.5.mlp.gate_proj.weight": "llamaforcausallm__model__layers__5__mlp__gate_proj__weight", "model.layers.5.mlp.up_proj.weight": "llamaforcausallm__model__layers__5__mlp__up_proj__weight", "model.layers.5.mlp.down_proj.weight": "llamaforcausallm__model__layers__5__mlp__down_proj__weight", "model.layers.5.input_layernorm.weight": "llamaforcausallm__model__layers__5__input_layernorm__weight", "model.layers.5.post_attention_layernorm.weight": "llamaforcausallm__model__layers__5__post_attention_layernorm__weight", "model.layers.6.self_attn.q_proj.weight": "llamaforcausallm__model__layers__6__self_attn__q_proj__weight", "model.layers.6.self_attn.k_proj.weight": "llamaforcausallm__model__layers__6__self_attn__k_proj__weight", "model.layers.6.self_attn.v_proj.weight": "llamaforcausallm__model__layers__6__self_attn__v_proj__weight", "model.layers.6.self_attn.o_proj.weight": "llamaforcausallm__model__layers__6__self_attn__o_proj__weight", "model.layers.6.mlp.gate_proj.weight": "llamaforcausallm__model__layers__6__mlp__gate_proj__weight", "model.layers.6.mlp.up_proj.weight": "llamaforcausallm__model__layers__6__mlp__up_proj__weight", "model.layers.6.mlp.down_proj.weight": "llamaforcausallm__model__layers__6__mlp__down_proj__weight", "model.layers.6.input_layernorm.weight": "llamaforcausallm__model__layers__6__input_layernorm__weight", "model.layers.6.post_attention_layernorm.weight": "llamaforcausallm__model__layers__6__post_attention_layernorm__weight", "model.layers.7.self_attn.q_proj.weight": "llamaforcausallm__model__layers__7__self_attn__q_proj__weight", "model.layers.7.self_attn.k_proj.weight": "llamaforcausallm__model__layers__7__self_attn__k_proj__weight", "model.layers.7.self_attn.v_proj.weight": "llamaforcausallm__model__layers__7__self_attn__v_proj__weight", "model.layers.7.self_attn.o_proj.weight": "llamaforcausallm__model__layers__7__self_attn__o_proj__weight", "model.layers.7.mlp.gate_proj.weight": "llamaforcausallm__model__layers__7__mlp__gate_proj__weight", "model.layers.7.mlp.up_proj.weight": "llamaforcausallm__model__layers__7__mlp__up_proj__weight", "model.layers.7.mlp.down_proj.weight": "llamaforcausallm__model__layers__7__mlp__down_proj__weight", "model.layers.7.input_layernorm.weight": "llamaforcausallm__model__layers__7__input_layernorm__weight", "model.layers.7.post_attention_layernorm.weight": "llamaforcausallm__model__layers__7__post_attention_layernorm__weight", "model.layers.8.self_attn.q_proj.weight": "llamaforcausallm__model__layers__8__self_attn__q_proj__weight", "model.layers.8.self_attn.k_proj.weight": "llamaforcausallm__model__layers__8__self_attn__k_proj__weight", "model.layers.8.self_attn.v_proj.weight": "llamaforcausallm__model__layers__8__self_attn__v_proj__weight", "model.layers.8.self_attn.o_proj.weight": "llamaforcausallm__model__layers__8__self_attn__o_proj__weight", "model.layers.8.mlp.gate_proj.weight": "llamaforcausallm__model__layers__8__mlp__gate_proj__weight", "model.layers.8.mlp.up_proj.weight": "llamaforcausallm__model__layers__8__mlp__up_proj__weight", "model.layers.8.mlp.down_proj.weight": "llamaforcausallm__model__layers__8__mlp__down_proj__weight", "model.layers.8.input_layernorm.weight": "llamaforcausallm__model__layers__8__input_layernorm__weight", "model.layers.8.post_attention_layernorm.weight": "llamaforcausallm__model__layers__8__post_attention_layernorm__weight", "model.layers.9.self_attn.q_proj.weight": "llamaforcausallm__model__layers__9__self_attn__q_proj__weight", "model.layers.9.self_attn.k_proj.weight": "llamaforcausallm__model__layers__9__self_attn__k_proj__weight", "model.layers.9.self_attn.v_proj.weight": "llamaforcausallm__model__layers__9__self_attn__v_proj__weight", "model.layers.9.self_attn.o_proj.weight": "llamaforcausallm__model__layers__9__self_attn__o_proj__weight", "model.layers.9.mlp.gate_proj.weight": "llamaforcausallm__model__layers__9__mlp__gate_proj__weight", "model.layers.9.mlp.up_proj.weight": "llamaforcausallm__model__layers__9__mlp__up_proj__weight", "model.layers.9.mlp.down_proj.weight": "llamaforcausallm__model__layers__9__mlp__down_proj__weight", "model.layers.9.input_layernorm.weight": "llamaforcausallm__model__layers__9__input_layernorm__weight", "model.layers.9.post_attention_layernorm.weight": "llamaforcausallm__model__layers__9__post_attention_layernorm__weight", "model.layers.10.self_attn.q_proj.weight": "llamaforcausallm__model__layers__10__self_attn__q_proj__weight", "model.layers.10.self_attn.k_proj.weight": "llamaforcausallm__model__layers__10__self_attn__k_proj__weight", "model.layers.10.self_attn.v_proj.weight": "llamaforcausallm__model__layers__10__self_attn__v_proj__weight", "model.layers.10.self_attn.o_proj.weight": "llamaforcausallm__model__layers__10__self_attn__o_proj__weight", "model.layers.10.mlp.gate_proj.weight": "llamaforcausallm__model__layers__10__mlp__gate_proj__weight", "model.layers.10.mlp.up_proj.weight": "llamaforcausallm__model__layers__10__mlp__up_proj__weight", "model.layers.10.mlp.down_proj.weight": "llamaforcausallm__model__layers__10__mlp__down_proj__weight", "model.layers.10.input_layernorm.weight": "llamaforcausallm__model__layers__10__input_layernorm__weight", "model.layers.10.post_attention_layernorm.weight": "llamaforcausallm__model__layers__10__post_attention_layernorm__weight", "model.layers.11.self_attn.q_proj.weight": "llamaforcausallm__model__layers__11__self_attn__q_proj__weight", "model.layers.11.self_attn.k_proj.weight": "llamaforcausallm__model__layers__11__self_attn__k_proj__weight", "model.layers.11.self_attn.v_proj.weight": "llamaforcausallm__model__layers__11__self_attn__v_proj__weight", "model.layers.11.self_attn.o_proj.weight": "llamaforcausallm__model__layers__11__self_attn__o_proj__weight", "model.layers.11.mlp.gate_proj.weight": "llamaforcausallm__model__layers__11__mlp__gate_proj__weight", "model.layers.11.mlp.up_proj.weight": "llamaforcausallm__model__layers__11__mlp__up_proj__weight", "model.layers.11.mlp.down_proj.weight": "llamaforcausallm__model__layers__11__mlp__down_proj__weight", "model.layers.11.input_layernorm.weight": "llamaforcausallm__model__layers__11__input_layernorm__weight", "model.layers.11.post_attention_layernorm.weight": "llamaforcausallm__model__layers__11__post_attention_layernorm__weight", "model.layers.12.self_attn.q_proj.weight": "llamaforcausallm__model__layers__12__self_attn__q_proj__weight", "model.layers.12.self_attn.k_proj.weight": "llamaforcausallm__model__layers__12__self_attn__k_proj__weight", "model.layers.12.self_attn.v_proj.weight": "llamaforcausallm__model__layers__12__self_attn__v_proj__weight", "model.layers.12.self_attn.o_proj.weight": "llamaforcausallm__model__layers__12__self_attn__o_proj__weight", "model.layers.12.mlp.gate_proj.weight": "llamaforcausallm__model__layers__12__mlp__gate_proj__weight", "model.layers.12.mlp.up_proj.weight": "llamaforcausallm__model__layers__12__mlp__up_proj__weight", "model.layers.12.mlp.down_proj.weight": "llamaforcausallm__model__layers__12__mlp__down_proj__weight", "model.layers.12.input_layernorm.weight": "llamaforcausallm__model__layers__12__input_layernorm__weight", "model.layers.12.post_attention_layernorm.weight": "llamaforcausallm__model__layers__12__post_attention_layernorm__weight", "model.layers.13.self_attn.q_proj.weight": "llamaforcausallm__model__layers__13__self_attn__q_proj__weight", "model.layers.13.self_attn.k_proj.weight": "llamaforcausallm__model__layers__13__self_attn__k_proj__weight", "model.layers.13.self_attn.v_proj.weight": "llamaforcausallm__model__layers__13__self_attn__v_proj__weight", "model.layers.13.self_attn.o_proj.weight": "llamaforcausallm__model__layers__13__self_attn__o_proj__weight", "model.layers.13.mlp.gate_proj.weight": "llamaforcausallm__model__layers__13__mlp__gate_proj__weight", "model.layers.13.mlp.up_proj.weight": "llamaforcausallm__model__layers__13__mlp__up_proj__weight", "model.layers.13.mlp.down_proj.weight": "llamaforcausallm__model__layers__13__mlp__down_proj__weight", "model.layers.13.input_layernorm.weight": "llamaforcausallm__model__layers__13__input_layernorm__weight", "model.layers.13.post_attention_layernorm.weight": "llamaforcausallm__model__layers__13__post_attention_layernorm__weight", "model.layers.14.self_attn.q_proj.weight": "llamaforcausallm__model__layers__14__self_attn__q_proj__weight", "model.layers.14.self_attn.k_proj.weight": "llamaforcausallm__model__layers__14__self_attn__k_proj__weight", "model.layers.14.self_attn.v_proj.weight": "llamaforcausallm__model__layers__14__self_attn__v_proj__weight", "model.layers.14.self_attn.o_proj.weight": "llamaforcausallm__model__layers__14__self_attn__o_proj__weight", "model.layers.14.mlp.gate_proj.weight": "llamaforcausallm__model__layers__14__mlp__gate_proj__weight", "model.layers.14.mlp.up_proj.weight": "llamaforcausallm__model__layers__14__mlp__up_proj__weight", "model.layers.14.mlp.down_proj.weight": "llamaforcausallm__model__layers__14__mlp__down_proj__weight", "model.layers.14.input_layernorm.weight": "llamaforcausallm__model__layers__14__input_layernorm__weight", "model.layers.14.post_attention_layernorm.weight": "llamaforcausallm__model__layers__14__post_attention_layernorm__weight", "model.layers.15.self_attn.q_proj.weight": "llamaforcausallm__model__layers__15__self_attn__q_proj__weight", "model.layers.15.self_attn.k_proj.weight": "llamaforcausallm__model__layers__15__self_attn__k_proj__weight", "model.layers.15.self_attn.v_proj.weight": "llamaforcausallm__model__layers__15__self_attn__v_proj__weight", "model.layers.15.self_attn.o_proj.weight": "llamaforcausallm__model__layers__15__self_attn__o_proj__weight", "model.layers.15.mlp.gate_proj.weight": "llamaforcausallm__model__layers__15__mlp__gate_proj__weight", "model.layers.15.mlp.up_proj.weight": "llamaforcausallm__model__layers__15__mlp__up_proj__weight", "model.layers.15.mlp.down_proj.weight": "llamaforcausallm__model__layers__15__mlp__down_proj__weight", "model.layers.15.input_layernorm.weight": "llamaforcausallm__model__layers__15__input_layernorm__weight", "model.layers.15.post_attention_layernorm.weight": "llamaforcausallm__model__layers__15__post_attention_layernorm__weight", "model.layers.16.self_attn.q_proj.weight": "llamaforcausallm__model__layers__16__self_attn__q_proj__weight", "model.layers.16.self_attn.k_proj.weight": "llamaforcausallm__model__layers__16__self_attn__k_proj__weight", "model.layers.16.self_attn.v_proj.weight": "llamaforcausallm__model__layers__16__self_attn__v_proj__weight", "model.layers.16.self_attn.o_proj.weight": "llamaforcausallm__model__layers__16__self_attn__o_proj__weight", "model.layers.16.mlp.gate_proj.weight": "llamaforcausallm__model__layers__16__mlp__gate_proj__weight", "model.layers.16.mlp.up_proj.weight": "llamaforcausallm__model__layers__16__mlp__up_proj__weight", "model.layers.16.mlp.down_proj.weight": "llamaforcausallm__model__layers__16__mlp__down_proj__weight", "model.layers.16.input_layernorm.weight": "llamaforcausallm__model__layers__16__input_layernorm__weight", "model.layers.16.post_attention_layernorm.weight": "llamaforcausallm__model__layers__16__post_attention_layernorm__weight", "model.layers.17.self_attn.q_proj.weight": "llamaforcausallm__model__layers__17__self_attn__q_proj__weight", "model.layers.17.self_attn.k_proj.weight": "llamaforcausallm__model__layers__17__self_attn__k_proj__weight", "model.layers.17.self_attn.v_proj.weight": "llamaforcausallm__model__layers__17__self_attn__v_proj__weight", "model.layers.17.self_attn.o_proj.weight": "llamaforcausallm__model__layers__17__self_attn__o_proj__weight", "model.layers.17.mlp.gate_proj.weight": "llamaforcausallm__model__layers__17__mlp__gate_proj__weight", "model.layers.17.mlp.up_proj.weight": "llamaforcausallm__model__layers__17__mlp__up_proj__weight", "model.layers.17.mlp.down_proj.weight": "llamaforcausallm__model__layers__17__mlp__down_proj__weight", "model.layers.17.input_layernorm.weight": "llamaforcausallm__model__layers__17__input_layernorm__weight", "model.layers.17.post_attention_layernorm.weight": "llamaforcausallm__model__layers__17__post_attention_layernorm__weight", "model.layers.18.self_attn.q_proj.weight": "llamaforcausallm__model__layers__18__self_attn__q_proj__weight", "model.layers.18.self_attn.k_proj.weight": "llamaforcausallm__model__layers__18__self_attn__k_proj__weight", "model.layers.18.self_attn.v_proj.weight": "llamaforcausallm__model__layers__18__self_attn__v_proj__weight", "model.layers.18.self_attn.o_proj.weight": "llamaforcausallm__model__layers__18__self_attn__o_proj__weight", "model.layers.18.mlp.gate_proj.weight": "llamaforcausallm__model__layers__18__mlp__gate_proj__weight", "model.layers.18.mlp.up_proj.weight": "llamaforcausallm__model__layers__18__mlp__up_proj__weight", "model.layers.18.mlp.down_proj.weight": "llamaforcausallm__model__layers__18__mlp__down_proj__weight", "model.layers.18.input_layernorm.weight": "llamaforcausallm__model__layers__18__input_layernorm__weight", "model.layers.18.post_attention_layernorm.weight": "llamaforcausallm__model__layers__18__post_attention_layernorm__weight", "model.layers.19.self_attn.q_proj.weight": "llamaforcausallm__model__layers__19__self_attn__q_proj__weight", "model.layers.19.self_attn.k_proj.weight": "llamaforcausallm__model__layers__19__self_attn__k_proj__weight", "model.layers.19.self_attn.v_proj.weight": "llamaforcausallm__model__layers__19__self_attn__v_proj__weight", "model.layers.19.self_attn.o_proj.weight": "llamaforcausallm__model__layers__19__self_attn__o_proj__weight", "model.layers.19.mlp.gate_proj.weight": "llamaforcausallm__model__layers__19__mlp__gate_proj__weight", "model.layers.19.mlp.up_proj.weight": "llamaforcausallm__model__layers__19__mlp__up_proj__weight", "model.layers.19.mlp.down_proj.weight": "llamaforcausallm__model__layers__19__mlp__down_proj__weight", "model.layers.19.input_layernorm.weight": "llamaforcausallm__model__layers__19__input_layernorm__weight", "model.layers.19.post_attention_layernorm.weight": "llamaforcausallm__model__layers__19__post_attention_layernorm__weight", "model.layers.20.self_attn.q_proj.weight": "llamaforcausallm__model__layers__20__self_attn__q_proj__weight", "model.layers.20.self_attn.k_proj.weight": "llamaforcausallm__model__layers__20__self_attn__k_proj__weight", "model.layers.20.self_attn.v_proj.weight": "llamaforcausallm__model__layers__20__self_attn__v_proj__weight", "model.layers.20.self_attn.o_proj.weight": "llamaforcausallm__model__layers__20__self_attn__o_proj__weight", "model.layers.20.mlp.gate_proj.weight": "llamaforcausallm__model__layers__20__mlp__gate_proj__weight", "model.layers.20.mlp.up_proj.weight": "llamaforcausallm__model__layers__20__mlp__up_proj__weight", "model.layers.20.mlp.down_proj.weight": "llamaforcausallm__model__layers__20__mlp__down_proj__weight", "model.layers.20.input_layernorm.weight": "llamaforcausallm__model__layers__20__input_layernorm__weight", "model.layers.20.post_attention_layernorm.weight": "llamaforcausallm__model__layers__20__post_attention_layernorm__weight", "model.layers.21.self_attn.q_proj.weight": "llamaforcausallm__model__layers__21__self_attn__q_proj__weight", "model.layers.21.self_attn.k_proj.weight": "llamaforcausallm__model__layers__21__self_attn__k_proj__weight", "model.layers.21.self_attn.v_proj.weight": "llamaforcausallm__model__layers__21__self_attn__v_proj__weight", "model.layers.21.self_attn.o_proj.weight": "llamaforcausallm__model__layers__21__self_attn__o_proj__weight", "model.layers.21.mlp.gate_proj.weight": "llamaforcausallm__model__layers__21__mlp__gate_proj__weight", "model.layers.21.mlp.up_proj.weight": "llamaforcausallm__model__layers__21__mlp__up_proj__weight", "model.layers.21.mlp.down_proj.weight": "llamaforcausallm__model__layers__21__mlp__down_proj__weight", "model.layers.21.input_layernorm.weight": "llamaforcausallm__model__layers__21__input_layernorm__weight", "model.layers.21.post_attention_layernorm.weight": "llamaforcausallm__model__layers__21__post_attention_layernorm__weight", "model.layers.22.self_attn.q_proj.weight": "llamaforcausallm__model__layers__22__self_attn__q_proj__weight", "model.layers.22.self_attn.k_proj.weight": "llamaforcausallm__model__layers__22__self_attn__k_proj__weight", "model.layers.22.self_attn.v_proj.weight": "llamaforcausallm__model__layers__22__self_attn__v_proj__weight", "model.layers.22.self_attn.o_proj.weight": "llamaforcausallm__model__layers__22__self_attn__o_proj__weight", "model.layers.22.mlp.gate_proj.weight": "llamaforcausallm__model__layers__22__mlp__gate_proj__weight", "model.layers.22.mlp.up_proj.weight": "llamaforcausallm__model__layers__22__mlp__up_proj__weight", "model.layers.22.mlp.down_proj.weight": "llamaforcausallm__model__layers__22__mlp__down_proj__weight", "model.layers.22.input_layernorm.weight": "llamaforcausallm__model__layers__22__input_layernorm__weight", "model.layers.22.post_attention_layernorm.weight": "llamaforcausallm__model__layers__22__post_attention_layernorm__weight", "model.layers.23.self_attn.q_proj.weight": "llamaforcausallm__model__layers__23__self_attn__q_proj__weight", "model.layers.23.self_attn.k_proj.weight": "llamaforcausallm__model__layers__23__self_attn__k_proj__weight", "model.layers.23.self_attn.v_proj.weight": "llamaforcausallm__model__layers__23__self_attn__v_proj__weight", "model.layers.23.self_attn.o_proj.weight": "llamaforcausallm__model__layers__23__self_attn__o_proj__weight", "model.layers.23.mlp.gate_proj.weight": "llamaforcausallm__model__layers__23__mlp__gate_proj__weight", "model.layers.23.mlp.up_proj.weight": "llamaforcausallm__model__layers__23__mlp__up_proj__weight", "model.layers.23.mlp.down_proj.weight": "llamaforcausallm__model__layers__23__mlp__down_proj__weight", "model.layers.23.input_layernorm.weight": "llamaforcausallm__model__layers__23__input_layernorm__weight", "model.layers.23.post_attention_layernorm.weight": "llamaforcausallm__model__layers__23__post_attention_layernorm__weight", "model.layers.24.self_attn.q_proj.weight": "llamaforcausallm__model__layers__24__self_attn__q_proj__weight", "model.layers.24.self_attn.k_proj.weight": "llamaforcausallm__model__layers__24__self_attn__k_proj__weight", "model.layers.24.self_attn.v_proj.weight": "llamaforcausallm__model__layers__24__self_attn__v_proj__weight", "model.layers.24.self_attn.o_proj.weight": "llamaforcausallm__model__layers__24__self_attn__o_proj__weight", "model.layers.24.mlp.gate_proj.weight": "llamaforcausallm__model__layers__24__mlp__gate_proj__weight", "model.layers.24.mlp.up_proj.weight": "llamaforcausallm__model__layers__24__mlp__up_proj__weight", "model.layers.24.mlp.down_proj.weight": "llamaforcausallm__model__layers__24__mlp__down_proj__weight", "model.layers.24.input_layernorm.weight": "llamaforcausallm__model__layers__24__input_layernorm__weight", "model.layers.24.post_attention_layernorm.weight": "llamaforcausallm__model__layers__24__post_attention_layernorm__weight", "model.layers.25.self_attn.q_proj.weight": "llamaforcausallm__model__layers__25__self_attn__q_proj__weight", "model.layers.25.self_attn.k_proj.weight": "llamaforcausallm__model__layers__25__self_attn__k_proj__weight", "model.layers.25.self_attn.v_proj.weight": "llamaforcausallm__model__layers__25__self_attn__v_proj__weight", "model.layers.25.self_attn.o_proj.weight": "llamaforcausallm__model__layers__25__self_attn__o_proj__weight", "model.layers.25.mlp.gate_proj.weight": "llamaforcausallm__model__layers__25__mlp__gate_proj__weight", "model.layers.25.mlp.up_proj.weight": "llamaforcausallm__model__layers__25__mlp__up_proj__weight", "model.layers.25.mlp.down_proj.weight": "llamaforcausallm__model__layers__25__mlp__down_proj__weight", "model.layers.25.input_layernorm.weight": "llamaforcausallm__model__layers__25__input_layernorm__weight", "model.layers.25.post_attention_layernorm.weight": "llamaforcausallm__model__layers__25__post_attention_layernorm__weight", "model.layers.26.self_attn.q_proj.weight": "llamaforcausallm__model__layers__26__self_attn__q_proj__weight", "model.layers.26.self_attn.k_proj.weight": "llamaforcausallm__model__layers__26__self_attn__k_proj__weight", "model.layers.26.self_attn.v_proj.weight": "llamaforcausallm__model__layers__26__self_attn__v_proj__weight", "model.layers.26.self_attn.o_proj.weight": "llamaforcausallm__model__layers__26__self_attn__o_proj__weight", "model.layers.26.mlp.gate_proj.weight": "llamaforcausallm__model__layers__26__mlp__gate_proj__weight", "model.layers.26.mlp.up_proj.weight": "llamaforcausallm__model__layers__26__mlp__up_proj__weight", "model.layers.26.mlp.down_proj.weight": "llamaforcausallm__model__layers__26__mlp__down_proj__weight", "model.layers.26.input_layernorm.weight": "llamaforcausallm__model__layers__26__input_layernorm__weight", "model.layers.26.post_attention_layernorm.weight": "llamaforcausallm__model__layers__26__post_attention_layernorm__weight", "model.layers.27.self_attn.q_proj.weight": "llamaforcausallm__model__layers__27__self_attn__q_proj__weight", "model.layers.27.self_attn.k_proj.weight": "llamaforcausallm__model__layers__27__self_attn__k_proj__weight", "model.layers.27.self_attn.v_proj.weight": "llamaforcausallm__model__layers__27__self_attn__v_proj__weight", "model.layers.27.self_attn.o_proj.weight": "llamaforcausallm__model__layers__27__self_attn__o_proj__weight", "model.layers.27.mlp.gate_proj.weight": "llamaforcausallm__model__layers__27__mlp__gate_proj__weight", "model.layers.27.mlp.up_proj.weight": "llamaforcausallm__model__layers__27__mlp__up_proj__weight", "model.layers.27.mlp.down_proj.weight": "llamaforcausallm__model__layers__27__mlp__down_proj__weight", "model.layers.27.input_layernorm.weight": "llamaforcausallm__model__layers__27__input_layernorm__weight", "model.layers.27.post_attention_layernorm.weight": "llamaforcausallm__model__layers__27__post_attention_layernorm__weight", "model.layers.28.self_attn.q_proj.weight": "llamaforcausallm__model__layers__28__self_attn__q_proj__weight", "model.layers.28.self_attn.k_proj.weight": "llamaforcausallm__model__layers__28__self_attn__k_proj__weight", "model.layers.28.self_attn.v_proj.weight": "llamaforcausallm__model__layers__28__self_attn__v_proj__weight", "model.layers.28.self_attn.o_proj.weight": "llamaforcausallm__model__layers__28__self_attn__o_proj__weight", "model.layers.28.mlp.gate_proj.weight": "llamaforcausallm__model__layers__28__mlp__gate_proj__weight", "model.layers.28.mlp.up_proj.weight": "llamaforcausallm__model__layers__28__mlp__up_proj__weight", "model.layers.28.mlp.down_proj.weight": "llamaforcausallm__model__layers__28__mlp__down_proj__weight", "model.layers.28.input_layernorm.weight": "llamaforcausallm__model__layers__28__input_layernorm__weight", "model.layers.28.post_attention_layernorm.weight": "llamaforcausallm__model__layers__28__post_attention_layernorm__weight", "model.layers.29.self_attn.q_proj.weight": "llamaforcausallm__model__layers__29__self_attn__q_proj__weight", "model.layers.29.self_attn.k_proj.weight": "llamaforcausallm__model__layers__29__self_attn__k_proj__weight", "model.layers.29.self_attn.v_proj.weight": "llamaforcausallm__model__layers__29__self_attn__v_proj__weight", "model.layers.29.self_attn.o_proj.weight": "llamaforcausallm__model__layers__29__self_attn__o_proj__weight", "model.layers.29.mlp.gate_proj.weight": "llamaforcausallm__model__layers__29__mlp__gate_proj__weight", "model.layers.29.mlp.up_proj.weight": "llamaforcausallm__model__layers__29__mlp__up_proj__weight", "model.layers.29.mlp.down_proj.weight": "llamaforcausallm__model__layers__29__mlp__down_proj__weight", "model.layers.29.input_layernorm.weight": "llamaforcausallm__model__layers__29__input_layernorm__weight", "model.layers.29.post_attention_layernorm.weight": "llamaforcausallm__model__layers__29__post_attention_layernorm__weight", "model.layers.30.self_attn.q_proj.weight": "llamaforcausallm__model__layers__30__self_attn__q_proj__weight", "model.layers.30.self_attn.k_proj.weight": "llamaforcausallm__model__layers__30__self_attn__k_proj__weight", "model.layers.30.self_attn.v_proj.weight": "llamaforcausallm__model__layers__30__self_attn__v_proj__weight", "model.layers.30.self_attn.o_proj.weight": "llamaforcausallm__model__layers__30__self_attn__o_proj__weight", "model.layers.30.mlp.gate_proj.weight": "llamaforcausallm__model__layers__30__mlp__gate_proj__weight", "model.layers.30.mlp.up_proj.weight": "llamaforcausallm__model__layers__30__mlp__up_proj__weight", "model.layers.30.mlp.down_proj.weight": "llamaforcausallm__model__layers__30__mlp__down_proj__weight", "model.layers.30.input_layernorm.weight": "llamaforcausallm__model__layers__30__input_layernorm__weight", "model.layers.30.post_attention_layernorm.weight": "llamaforcausallm__model__layers__30__post_attention_layernorm__weight", "model.layers.31.self_attn.q_proj.weight": "llamaforcausallm__model__layers__31__self_attn__q_proj__weight", "model.layers.31.self_attn.k_proj.weight": "llamaforcausallm__model__layers__31__self_attn__k_proj__weight", "model.layers.31.self_attn.v_proj.weight": "llamaforcausallm__model__layers__31__self_attn__v_proj__weight", "model.layers.31.self_attn.o_proj.weight": "llamaforcausallm__model__layers__31__self_attn__o_proj__weight", "model.layers.31.mlp.gate_proj.weight": "llamaforcausallm__model__layers__31__mlp__gate_proj__weight", "model.layers.31.mlp.up_proj.weight": "llamaforcausallm__model__layers__31__mlp__up_proj__weight", "model.layers.31.mlp.down_proj.weight": "llamaforcausallm__model__layers__31__mlp__down_proj__weight", "model.layers.31.input_layernorm.weight": "llamaforcausallm__model__layers__31__input_layernorm__weight", "model.layers.31.post_attention_layernorm.weight": "llamaforcausallm__model__layers__31__post_attention_layernorm__weight", "model.layers.32.self_attn.q_proj.weight": "llamaforcausallm__model__layers__32__self_attn__q_proj__weight", "model.layers.32.self_attn.k_proj.weight": "llamaforcausallm__model__layers__32__self_attn__k_proj__weight", "model.layers.32.self_attn.v_proj.weight": "llamaforcausallm__model__layers__32__self_attn__v_proj__weight", "model.layers.32.self_attn.o_proj.weight": "llamaforcausallm__model__layers__32__self_attn__o_proj__weight", "model.layers.32.mlp.gate_proj.weight": "llamaforcausallm__model__layers__32__mlp__gate_proj__weight", "model.layers.32.mlp.up_proj.weight": "llamaforcausallm__model__layers__32__mlp__up_proj__weight", "model.layers.32.mlp.down_proj.weight": "llamaforcausallm__model__layers__32__mlp__down_proj__weight", "model.layers.32.input_layernorm.weight": "llamaforcausallm__model__layers__32__input_layernorm__weight", "model.layers.32.post_attention_layernorm.weight": "llamaforcausallm__model__layers__32__post_attention_layernorm__weight", "model.layers.33.self_attn.q_proj.weight": "llamaforcausallm__model__layers__33__self_attn__q_proj__weight", "model.layers.33.self_attn.k_proj.weight": "llamaforcausallm__model__layers__33__self_attn__k_proj__weight", "model.layers.33.self_attn.v_proj.weight": "llamaforcausallm__model__layers__33__self_attn__v_proj__weight", "model.layers.33.self_attn.o_proj.weight": "llamaforcausallm__model__layers__33__self_attn__o_proj__weight", "model.layers.33.mlp.gate_proj.weight": "llamaforcausallm__model__layers__33__mlp__gate_proj__weight", "model.layers.33.mlp.up_proj.weight": "llamaforcausallm__model__layers__33__mlp__up_proj__weight", "model.layers.33.mlp.down_proj.weight": "llamaforcausallm__model__layers__33__mlp__down_proj__weight", "model.layers.33.input_layernorm.weight": "llamaforcausallm__model__layers__33__input_layernorm__weight", "model.layers.33.post_attention_layernorm.weight": "llamaforcausallm__model__layers__33__post_attention_layernorm__weight", "model.layers.34.self_attn.q_proj.weight": "llamaforcausallm__model__layers__34__self_attn__q_proj__weight", "model.layers.34.self_attn.k_proj.weight": "llamaforcausallm__model__layers__34__self_attn__k_proj__weight", "model.layers.34.self_attn.v_proj.weight": "llamaforcausallm__model__layers__34__self_attn__v_proj__weight", "model.layers.34.self_attn.o_proj.weight": "llamaforcausallm__model__layers__34__self_attn__o_proj__weight", "model.layers.34.mlp.gate_proj.weight": "llamaforcausallm__model__layers__34__mlp__gate_proj__weight", "model.layers.34.mlp.up_proj.weight": "llamaforcausallm__model__layers__34__mlp__up_proj__weight", "model.layers.34.mlp.down_proj.weight": "llamaforcausallm__model__layers__34__mlp__down_proj__weight", "model.layers.34.input_layernorm.weight": "llamaforcausallm__model__layers__34__input_layernorm__weight", "model.layers.34.post_attention_layernorm.weight": "llamaforcausallm__model__layers__34__post_attention_layernorm__weight", "model.layers.35.self_attn.q_proj.weight": "llamaforcausallm__model__layers__35__self_attn__q_proj__weight", "model.layers.35.self_attn.k_proj.weight": "llamaforcausallm__model__layers__35__self_attn__k_proj__weight", "model.layers.35.self_attn.v_proj.weight": "llamaforcausallm__model__layers__35__self_attn__v_proj__weight", "model.layers.35.self_attn.o_proj.weight": "llamaforcausallm__model__layers__35__self_attn__o_proj__weight", "model.layers.35.mlp.gate_proj.weight": "llamaforcausallm__model__layers__35__mlp__gate_proj__weight", "model.layers.35.mlp.up_proj.weight": "llamaforcausallm__model__layers__35__mlp__up_proj__weight", "model.layers.35.mlp.down_proj.weight": "llamaforcausallm__model__layers__35__mlp__down_proj__weight", "model.layers.35.input_layernorm.weight": "llamaforcausallm__model__layers__35__input_layernorm__weight", "model.layers.35.post_attention_layernorm.weight": "llamaforcausallm__model__layers__35__post_attention_layernorm__weight", "model.layers.36.self_attn.q_proj.weight": "llamaforcausallm__model__layers__36__self_attn__q_proj__weight", "model.layers.36.self_attn.k_proj.weight": "llamaforcausallm__model__layers__36__self_attn__k_proj__weight", "model.layers.36.self_attn.v_proj.weight": "llamaforcausallm__model__layers__36__self_attn__v_proj__weight", "model.layers.36.self_attn.o_proj.weight": "llamaforcausallm__model__layers__36__self_attn__o_proj__weight", "model.layers.36.mlp.gate_proj.weight": "llamaforcausallm__model__layers__36__mlp__gate_proj__weight", "model.layers.36.mlp.up_proj.weight": "llamaforcausallm__model__layers__36__mlp__up_proj__weight", "model.layers.36.mlp.down_proj.weight": "llamaforcausallm__model__layers__36__mlp__down_proj__weight", "model.layers.36.input_layernorm.weight": "llamaforcausallm__model__layers__36__input_layernorm__weight", "model.layers.36.post_attention_layernorm.weight": "llamaforcausallm__model__layers__36__post_attention_layernorm__weight", "model.layers.37.self_attn.q_proj.weight": "llamaforcausallm__model__layers__37__self_attn__q_proj__weight", "model.layers.37.self_attn.k_proj.weight": "llamaforcausallm__model__layers__37__self_attn__k_proj__weight", "model.layers.37.self_attn.v_proj.weight": "llamaforcausallm__model__layers__37__self_attn__v_proj__weight", "model.layers.37.self_attn.o_proj.weight": "llamaforcausallm__model__layers__37__self_attn__o_proj__weight", "model.layers.37.mlp.gate_proj.weight": "llamaforcausallm__model__layers__37__mlp__gate_proj__weight", "model.layers.37.mlp.up_proj.weight": "llamaforcausallm__model__layers__37__mlp__up_proj__weight", "model.layers.37.mlp.down_proj.weight": "llamaforcausallm__model__layers__37__mlp__down_proj__weight", "model.layers.37.input_layernorm.weight": "llamaforcausallm__model__layers__37__input_layernorm__weight", "model.layers.37.post_attention_layernorm.weight": "llamaforcausallm__model__layers__37__post_attention_layernorm__weight", "model.layers.38.self_attn.q_proj.weight": "llamaforcausallm__model__layers__38__self_attn__q_proj__weight", "model.layers.38.self_attn.k_proj.weight": "llamaforcausallm__model__layers__38__self_attn__k_proj__weight", "model.layers.38.self_attn.v_proj.weight": "llamaforcausallm__model__layers__38__self_attn__v_proj__weight", "model.layers.38.self_attn.o_proj.weight": "llamaforcausallm__model__layers__38__self_attn__o_proj__weight", "model.layers.38.mlp.gate_proj.weight": "llamaforcausallm__model__layers__38__mlp__gate_proj__weight", "model.layers.38.mlp.up_proj.weight": "llamaforcausallm__model__layers__38__mlp__up_proj__weight", "model.layers.38.mlp.down_proj.weight": "llamaforcausallm__model__layers__38__mlp__down_proj__weight", "model.layers.38.input_layernorm.weight": "llamaforcausallm__model__layers__38__input_layernorm__weight", "model.layers.38.post_attention_layernorm.weight": "llamaforcausallm__model__layers__38__post_attention_layernorm__weight", "model.layers.39.self_attn.q_proj.weight": "llamaforcausallm__model__layers__39__self_attn__q_proj__weight", "model.layers.39.self_attn.k_proj.weight": "llamaforcausallm__model__layers__39__self_attn__k_proj__weight", "model.layers.39.self_attn.v_proj.weight": "llamaforcausallm__model__layers__39__self_attn__v_proj__weight", "model.layers.39.self_attn.o_proj.weight": "llamaforcausallm__model__layers__39__self_attn__o_proj__weight", "model.layers.39.mlp.gate_proj.weight": "llamaforcausallm__model__layers__39__mlp__gate_proj__weight", "model.layers.39.mlp.up_proj.weight": "llamaforcausallm__model__layers__39__mlp__up_proj__weight", "model.layers.39.mlp.down_proj.weight": "llamaforcausallm__model__layers__39__mlp__down_proj__weight", "model.layers.39.input_layernorm.weight": "llamaforcausallm__model__layers__39__input_layernorm__weight", "model.layers.39.post_attention_layernorm.weight": "llamaforcausallm__model__layers__39__post_attention_layernorm__weight", "model.layers.40.self_attn.q_proj.weight": "llamaforcausallm__model__layers__40__self_attn__q_proj__weight", "model.layers.40.self_attn.k_proj.weight": "llamaforcausallm__model__layers__40__self_attn__k_proj__weight", "model.layers.40.self_attn.v_proj.weight": "llamaforcausallm__model__layers__40__self_attn__v_proj__weight", "model.layers.40.self_attn.o_proj.weight": "llamaforcausallm__model__layers__40__self_attn__o_proj__weight", "model.layers.40.mlp.gate_proj.weight": "llamaforcausallm__model__layers__40__mlp__gate_proj__weight", "model.layers.40.mlp.up_proj.weight": "llamaforcausallm__model__layers__40__mlp__up_proj__weight", "model.layers.40.mlp.down_proj.weight": "llamaforcausallm__model__layers__40__mlp__down_proj__weight", "model.layers.40.input_layernorm.weight": "llamaforcausallm__model__layers__40__input_layernorm__weight", "model.layers.40.post_attention_layernorm.weight": "llamaforcausallm__model__layers__40__post_attention_layernorm__weight", "model.layers.41.self_attn.q_proj.weight": "llamaforcausallm__model__layers__41__self_attn__q_proj__weight", "model.layers.41.self_attn.k_proj.weight": "llamaforcausallm__model__layers__41__self_attn__k_proj__weight", "model.layers.41.self_attn.v_proj.weight": "llamaforcausallm__model__layers__41__self_attn__v_proj__weight", "model.layers.41.self_attn.o_proj.weight": "llamaforcausallm__model__layers__41__self_attn__o_proj__weight", "model.layers.41.mlp.gate_proj.weight": "llamaforcausallm__model__layers__41__mlp__gate_proj__weight", "model.layers.41.mlp.up_proj.weight": "llamaforcausallm__model__layers__41__mlp__up_proj__weight", "model.layers.41.mlp.down_proj.weight": "llamaforcausallm__model__layers__41__mlp__down_proj__weight", "model.layers.41.input_layernorm.weight": "llamaforcausallm__model__layers__41__input_layernorm__weight", "model.layers.41.post_attention_layernorm.weight": "llamaforcausallm__model__layers__41__post_attention_layernorm__weight", "model.layers.42.self_attn.q_proj.weight": "llamaforcausallm__model__layers__42__self_attn__q_proj__weight", "model.layers.42.self_attn.k_proj.weight": "llamaforcausallm__model__layers__42__self_attn__k_proj__weight", "model.layers.42.self_attn.v_proj.weight": "llamaforcausallm__model__layers__42__self_attn__v_proj__weight", "model.layers.42.self_attn.o_proj.weight": "llamaforcausallm__model__layers__42__self_attn__o_proj__weight", "model.layers.42.mlp.gate_proj.weight": "llamaforcausallm__model__layers__42__mlp__gate_proj__weight", "model.layers.42.mlp.up_proj.weight": "llamaforcausallm__model__layers__42__mlp__up_proj__weight", "model.layers.42.mlp.down_proj.weight": "llamaforcausallm__model__layers__42__mlp__down_proj__weight", "model.layers.42.input_layernorm.weight": "llamaforcausallm__model__layers__42__input_layernorm__weight", "model.layers.42.post_attention_layernorm.weight": "llamaforcausallm__model__layers__42__post_attention_layernorm__weight", "model.layers.43.self_attn.q_proj.weight": "llamaforcausallm__model__layers__43__self_attn__q_proj__weight", "model.layers.43.self_attn.k_proj.weight": "llamaforcausallm__model__layers__43__self_attn__k_proj__weight", "model.layers.43.self_attn.v_proj.weight": "llamaforcausallm__model__layers__43__self_attn__v_proj__weight", "model.layers.43.self_attn.o_proj.weight": "llamaforcausallm__model__layers__43__self_attn__o_proj__weight", "model.layers.43.mlp.gate_proj.weight": "llamaforcausallm__model__layers__43__mlp__gate_proj__weight", "model.layers.43.mlp.up_proj.weight": "llamaforcausallm__model__layers__43__mlp__up_proj__weight", "model.layers.43.mlp.down_proj.weight": "llamaforcausallm__model__layers__43__mlp__down_proj__weight", "model.layers.43.input_layernorm.weight": "llamaforcausallm__model__layers__43__input_layernorm__weight", "model.layers.43.post_attention_layernorm.weight": "llamaforcausallm__model__layers__43__post_attention_layernorm__weight", "model.layers.44.self_attn.q_proj.weight": "llamaforcausallm__model__layers__44__self_attn__q_proj__weight", "model.layers.44.self_attn.k_proj.weight": "llamaforcausallm__model__layers__44__self_attn__k_proj__weight", "model.layers.44.self_attn.v_proj.weight": "llamaforcausallm__model__layers__44__self_attn__v_proj__weight", "model.layers.44.self_attn.o_proj.weight": "llamaforcausallm__model__layers__44__self_attn__o_proj__weight", "model.layers.44.mlp.gate_proj.weight": "llamaforcausallm__model__layers__44__mlp__gate_proj__weight", "model.layers.44.mlp.up_proj.weight": "llamaforcausallm__model__layers__44__mlp__up_proj__weight", "model.layers.44.mlp.down_proj.weight": "llamaforcausallm__model__layers__44__mlp__down_proj__weight", "model.layers.44.input_layernorm.weight": "llamaforcausallm__model__layers__44__input_layernorm__weight", "model.layers.44.post_attention_layernorm.weight": "llamaforcausallm__model__layers__44__post_attention_layernorm__weight", "model.layers.45.self_attn.q_proj.weight": "llamaforcausallm__model__layers__45__self_attn__q_proj__weight", "model.layers.45.self_attn.k_proj.weight": "llamaforcausallm__model__layers__45__self_attn__k_proj__weight", "model.layers.45.self_attn.v_proj.weight": "llamaforcausallm__model__layers__45__self_attn__v_proj__weight", "model.layers.45.self_attn.o_proj.weight": "llamaforcausallm__model__layers__45__self_attn__o_proj__weight", "model.layers.45.mlp.gate_proj.weight": "llamaforcausallm__model__layers__45__mlp__gate_proj__weight", "model.layers.45.mlp.up_proj.weight": "llamaforcausallm__model__layers__45__mlp__up_proj__weight", "model.layers.45.mlp.down_proj.weight": "llamaforcausallm__model__layers__45__mlp__down_proj__weight", "model.layers.45.input_layernorm.weight": "llamaforcausallm__model__layers__45__input_layernorm__weight", "model.layers.45.post_attention_layernorm.weight": "llamaforcausallm__model__layers__45__post_attention_layernorm__weight", "model.layers.46.self_attn.q_proj.weight": "llamaforcausallm__model__layers__46__self_attn__q_proj__weight", "model.layers.46.self_attn.k_proj.weight": "llamaforcausallm__model__layers__46__self_attn__k_proj__weight", "model.layers.46.self_attn.v_proj.weight": "llamaforcausallm__model__layers__46__self_attn__v_proj__weight", "model.layers.46.self_attn.o_proj.weight": "llamaforcausallm__model__layers__46__self_attn__o_proj__weight", "model.layers.46.mlp.gate_proj.weight": "llamaforcausallm__model__layers__46__mlp__gate_proj__weight", "model.layers.46.mlp.up_proj.weight": "llamaforcausallm__model__layers__46__mlp__up_proj__weight", "model.layers.46.mlp.down_proj.weight": "llamaforcausallm__model__layers__46__mlp__down_proj__weight", "model.layers.46.input_layernorm.weight": "llamaforcausallm__model__layers__46__input_layernorm__weight", "model.layers.46.post_attention_layernorm.weight": "llamaforcausallm__model__layers__46__post_attention_layernorm__weight", "model.layers.47.self_attn.q_proj.weight": "llamaforcausallm__model__layers__47__self_attn__q_proj__weight", "model.layers.47.self_attn.k_proj.weight": "llamaforcausallm__model__layers__47__self_attn__k_proj__weight", "model.layers.47.self_attn.v_proj.weight": "llamaforcausallm__model__layers__47__self_attn__v_proj__weight", "model.layers.47.self_attn.o_proj.weight": "llamaforcausallm__model__layers__47__self_attn__o_proj__weight", "model.layers.47.mlp.gate_proj.weight": "llamaforcausallm__model__layers__47__mlp__gate_proj__weight", "model.layers.47.mlp.up_proj.weight": "llamaforcausallm__model__layers__47__mlp__up_proj__weight", "model.layers.47.mlp.down_proj.weight": "llamaforcausallm__model__layers__47__mlp__down_proj__weight", "model.layers.47.input_layernorm.weight": "llamaforcausallm__model__layers__47__input_layernorm__weight", "model.layers.47.post_attention_layernorm.weight": "llamaforcausallm__model__layers__47__post_attention_layernorm__weight", "model.layers.48.self_attn.q_proj.weight": "llamaforcausallm__model__layers__48__self_attn__q_proj__weight", "model.layers.48.self_attn.k_proj.weight": "llamaforcausallm__model__layers__48__self_attn__k_proj__weight", "model.layers.48.self_attn.v_proj.weight": "llamaforcausallm__model__layers__48__self_attn__v_proj__weight", "model.layers.48.self_attn.o_proj.weight": "llamaforcausallm__model__layers__48__self_attn__o_proj__weight", "model.layers.48.mlp.gate_proj.weight": "llamaforcausallm__model__layers__48__mlp__gate_proj__weight", "model.layers.48.mlp.up_proj.weight": "llamaforcausallm__model__layers__48__mlp__up_proj__weight", "model.layers.48.mlp.down_proj.weight": "llamaforcausallm__model__layers__48__mlp__down_proj__weight", "model.layers.48.input_layernorm.weight": "llamaforcausallm__model__layers__48__input_layernorm__weight", "model.layers.48.post_attention_layernorm.weight": "llamaforcausallm__model__layers__48__post_attention_layernorm__weight", "model.layers.49.self_attn.q_proj.weight": "llamaforcausallm__model__layers__49__self_attn__q_proj__weight", "model.layers.49.self_attn.k_proj.weight": "llamaforcausallm__model__layers__49__self_attn__k_proj__weight", "model.layers.49.self_attn.v_proj.weight": "llamaforcausallm__model__layers__49__self_attn__v_proj__weight", "model.layers.49.self_attn.o_proj.weight": "llamaforcausallm__model__layers__49__self_attn__o_proj__weight", "model.layers.49.mlp.gate_proj.weight": "llamaforcausallm__model__layers__49__mlp__gate_proj__weight", "model.layers.49.mlp.up_proj.weight": "llamaforcausallm__model__layers__49__mlp__up_proj__weight", "model.layers.49.mlp.down_proj.weight": "llamaforcausallm__model__layers__49__mlp__down_proj__weight", "model.layers.49.input_layernorm.weight": "llamaforcausallm__model__layers__49__input_layernorm__weight", "model.layers.49.post_attention_layernorm.weight": "llamaforcausallm__model__layers__49__post_attention_layernorm__weight", "model.layers.50.self_attn.q_proj.weight": "llamaforcausallm__model__layers__50__self_attn__q_proj__weight", "model.layers.50.self_attn.k_proj.weight": "llamaforcausallm__model__layers__50__self_attn__k_proj__weight", "model.layers.50.self_attn.v_proj.weight": "llamaforcausallm__model__layers__50__self_attn__v_proj__weight", "model.layers.50.self_attn.o_proj.weight": "llamaforcausallm__model__layers__50__self_attn__o_proj__weight", "model.layers.50.mlp.gate_proj.weight": "llamaforcausallm__model__layers__50__mlp__gate_proj__weight", "model.layers.50.mlp.up_proj.weight": "llamaforcausallm__model__layers__50__mlp__up_proj__weight", "model.layers.50.mlp.down_proj.weight": "llamaforcausallm__model__layers__50__mlp__down_proj__weight", "model.layers.50.input_layernorm.weight": "llamaforcausallm__model__layers__50__input_layernorm__weight", "model.layers.50.post_attention_layernorm.weight": "llamaforcausallm__model__layers__50__post_attention_layernorm__weight", "model.layers.51.self_attn.q_proj.weight": "llamaforcausallm__model__layers__51__self_attn__q_proj__weight", "model.layers.51.self_attn.k_proj.weight": "llamaforcausallm__model__layers__51__self_attn__k_proj__weight", "model.layers.51.self_attn.v_proj.weight": "llamaforcausallm__model__layers__51__self_attn__v_proj__weight", "model.layers.51.self_attn.o_proj.weight": "llamaforcausallm__model__layers__51__self_attn__o_proj__weight", "model.layers.51.mlp.gate_proj.weight": "llamaforcausallm__model__layers__51__mlp__gate_proj__weight", "model.layers.51.mlp.up_proj.weight": "llamaforcausallm__model__layers__51__mlp__up_proj__weight", "model.layers.51.mlp.down_proj.weight": "llamaforcausallm__model__layers__51__mlp__down_proj__weight", "model.layers.51.input_layernorm.weight": "llamaforcausallm__model__layers__51__input_layernorm__weight", "model.layers.51.post_attention_layernorm.weight": "llamaforcausallm__model__layers__51__post_attention_layernorm__weight", "model.layers.52.self_attn.q_proj.weight": "llamaforcausallm__model__layers__52__self_attn__q_proj__weight", "model.layers.52.self_attn.k_proj.weight": "llamaforcausallm__model__layers__52__self_attn__k_proj__weight", "model.layers.52.self_attn.v_proj.weight": "llamaforcausallm__model__layers__52__self_attn__v_proj__weight", "model.layers.52.self_attn.o_proj.weight": "llamaforcausallm__model__layers__52__self_attn__o_proj__weight", "model.layers.52.mlp.gate_proj.weight": "llamaforcausallm__model__layers__52__mlp__gate_proj__weight", "model.layers.52.mlp.up_proj.weight": "llamaforcausallm__model__layers__52__mlp__up_proj__weight", "model.layers.52.mlp.down_proj.weight": "llamaforcausallm__model__layers__52__mlp__down_proj__weight", "model.layers.52.input_layernorm.weight": "llamaforcausallm__model__layers__52__input_layernorm__weight", "model.layers.52.post_attention_layernorm.weight": "llamaforcausallm__model__layers__52__post_attention_layernorm__weight", "model.layers.53.self_attn.q_proj.weight": "llamaforcausallm__model__layers__53__self_attn__q_proj__weight", "model.layers.53.self_attn.k_proj.weight": "llamaforcausallm__model__layers__53__self_attn__k_proj__weight", "model.layers.53.self_attn.v_proj.weight": "llamaforcausallm__model__layers__53__self_attn__v_proj__weight", "model.layers.53.self_attn.o_proj.weight": "llamaforcausallm__model__layers__53__self_attn__o_proj__weight", "model.layers.53.mlp.gate_proj.weight": "llamaforcausallm__model__layers__53__mlp__gate_proj__weight", "model.layers.53.mlp.up_proj.weight": "llamaforcausallm__model__layers__53__mlp__up_proj__weight", "model.layers.53.mlp.down_proj.weight": "llamaforcausallm__model__layers__53__mlp__down_proj__weight", "model.layers.53.input_layernorm.weight": "llamaforcausallm__model__layers__53__input_layernorm__weight", "model.layers.53.post_attention_layernorm.weight": "llamaforcausallm__model__layers__53__post_attention_layernorm__weight", "model.layers.54.self_attn.q_proj.weight": "llamaforcausallm__model__layers__54__self_attn__q_proj__weight", "model.layers.54.self_attn.k_proj.weight": "llamaforcausallm__model__layers__54__self_attn__k_proj__weight", "model.layers.54.self_attn.v_proj.weight": "llamaforcausallm__model__layers__54__self_attn__v_proj__weight", "model.layers.54.self_attn.o_proj.weight": "llamaforcausallm__model__layers__54__self_attn__o_proj__weight", "model.layers.54.mlp.gate_proj.weight": "llamaforcausallm__model__layers__54__mlp__gate_proj__weight", "model.layers.54.mlp.up_proj.weight": "llamaforcausallm__model__layers__54__mlp__up_proj__weight", "model.layers.54.mlp.down_proj.weight": "llamaforcausallm__model__layers__54__mlp__down_proj__weight", "model.layers.54.input_layernorm.weight": "llamaforcausallm__model__layers__54__input_layernorm__weight", "model.layers.54.post_attention_layernorm.weight": "llamaforcausallm__model__layers__54__post_attention_layernorm__weight", "model.layers.55.self_attn.q_proj.weight": "llamaforcausallm__model__layers__55__self_attn__q_proj__weight", "model.layers.55.self_attn.k_proj.weight": "llamaforcausallm__model__layers__55__self_attn__k_proj__weight", "model.layers.55.self_attn.v_proj.weight": "llamaforcausallm__model__layers__55__self_attn__v_proj__weight", "model.layers.55.self_attn.o_proj.weight": "llamaforcausallm__model__layers__55__self_attn__o_proj__weight", "model.layers.55.mlp.gate_proj.weight": "llamaforcausallm__model__layers__55__mlp__gate_proj__weight", "model.layers.55.mlp.up_proj.weight": "llamaforcausallm__model__layers__55__mlp__up_proj__weight", "model.layers.55.mlp.down_proj.weight": "llamaforcausallm__model__layers__55__mlp__down_proj__weight", "model.layers.55.input_layernorm.weight": "llamaforcausallm__model__layers__55__input_layernorm__weight", "model.layers.55.post_attention_layernorm.weight": "llamaforcausallm__model__layers__55__post_attention_layernorm__weight", "model.layers.56.self_attn.q_proj.weight": "llamaforcausallm__model__layers__56__self_attn__q_proj__weight", "model.layers.56.self_attn.k_proj.weight": "llamaforcausallm__model__layers__56__self_attn__k_proj__weight", "model.layers.56.self_attn.v_proj.weight": "llamaforcausallm__model__layers__56__self_attn__v_proj__weight", "model.layers.56.self_attn.o_proj.weight": "llamaforcausallm__model__layers__56__self_attn__o_proj__weight", "model.layers.56.mlp.gate_proj.weight": "llamaforcausallm__model__layers__56__mlp__gate_proj__weight", "model.layers.56.mlp.up_proj.weight": "llamaforcausallm__model__layers__56__mlp__up_proj__weight", "model.layers.56.mlp.down_proj.weight": "llamaforcausallm__model__layers__56__mlp__down_proj__weight", "model.layers.56.input_layernorm.weight": "llamaforcausallm__model__layers__56__input_layernorm__weight", "model.layers.56.post_attention_layernorm.weight": "llamaforcausallm__model__layers__56__post_attention_layernorm__weight", "model.layers.57.self_attn.q_proj.weight": "llamaforcausallm__model__layers__57__self_attn__q_proj__weight", "model.layers.57.self_attn.k_proj.weight": "llamaforcausallm__model__layers__57__self_attn__k_proj__weight", "model.layers.57.self_attn.v_proj.weight": "llamaforcausallm__model__layers__57__self_attn__v_proj__weight", "model.layers.57.self_attn.o_proj.weight": "llamaforcausallm__model__layers__57__self_attn__o_proj__weight", "model.layers.57.mlp.gate_proj.weight": "llamaforcausallm__model__layers__57__mlp__gate_proj__weight", "model.layers.57.mlp.up_proj.weight": "llamaforcausallm__model__layers__57__mlp__up_proj__weight", "model.layers.57.mlp.down_proj.weight": "llamaforcausallm__model__layers__57__mlp__down_proj__weight", "model.layers.57.input_layernorm.weight": "llamaforcausallm__model__layers__57__input_layernorm__weight", "model.layers.57.post_attention_layernorm.weight": "llamaforcausallm__model__layers__57__post_attention_layernorm__weight", "model.layers.58.self_attn.q_proj.weight": "llamaforcausallm__model__layers__58__self_attn__q_proj__weight", "model.layers.58.self_attn.k_proj.weight": "llamaforcausallm__model__layers__58__self_attn__k_proj__weight", "model.layers.58.self_attn.v_proj.weight": "llamaforcausallm__model__layers__58__self_attn__v_proj__weight", "model.layers.58.self_attn.o_proj.weight": "llamaforcausallm__model__layers__58__self_attn__o_proj__weight", "model.layers.58.mlp.gate_proj.weight": "llamaforcausallm__model__layers__58__mlp__gate_proj__weight", "model.layers.58.mlp.up_proj.weight": "llamaforcausallm__model__layers__58__mlp__up_proj__weight", "model.layers.58.mlp.down_proj.weight": "llamaforcausallm__model__layers__58__mlp__down_proj__weight", "model.layers.58.input_layernorm.weight": "llamaforcausallm__model__layers__58__input_layernorm__weight", "model.layers.58.post_attention_layernorm.weight": "llamaforcausallm__model__layers__58__post_attention_layernorm__weight", "model.layers.59.self_attn.q_proj.weight": "llamaforcausallm__model__layers__59__self_attn__q_proj__weight", "model.layers.59.self_attn.k_proj.weight": "llamaforcausallm__model__layers__59__self_attn__k_proj__weight", "model.layers.59.self_attn.v_proj.weight": "llamaforcausallm__model__layers__59__self_attn__v_proj__weight", "model.layers.59.self_attn.o_proj.weight": "llamaforcausallm__model__layers__59__self_attn__o_proj__weight", "model.layers.59.mlp.gate_proj.weight": "llamaforcausallm__model__layers__59__mlp__gate_proj__weight", "model.layers.59.mlp.up_proj.weight": "llamaforcausallm__model__layers__59__mlp__up_proj__weight", "model.layers.59.mlp.down_proj.weight": "llamaforcausallm__model__layers__59__mlp__down_proj__weight", "model.layers.59.input_layernorm.weight": "llamaforcausallm__model__layers__59__input_layernorm__weight", "model.layers.59.post_attention_layernorm.weight": "llamaforcausallm__model__layers__59__post_attention_layernorm__weight", "model.layers.60.self_attn.q_proj.weight": "llamaforcausallm__model__layers__60__self_attn__q_proj__weight", "model.layers.60.self_attn.k_proj.weight": "llamaforcausallm__model__layers__60__self_attn__k_proj__weight", "model.layers.60.self_attn.v_proj.weight": "llamaforcausallm__model__layers__60__self_attn__v_proj__weight", "model.layers.60.self_attn.o_proj.weight": "llamaforcausallm__model__layers__60__self_attn__o_proj__weight", "model.layers.60.mlp.gate_proj.weight": "llamaforcausallm__model__layers__60__mlp__gate_proj__weight", "model.layers.60.mlp.up_proj.weight": "llamaforcausallm__model__layers__60__mlp__up_proj__weight", "model.layers.60.mlp.down_proj.weight": "llamaforcausallm__model__layers__60__mlp__down_proj__weight", "model.layers.60.input_layernorm.weight": "llamaforcausallm__model__layers__60__input_layernorm__weight", "model.layers.60.post_attention_layernorm.weight": "llamaforcausallm__model__layers__60__post_attention_layernorm__weight", "model.layers.61.self_attn.q_proj.weight": "llamaforcausallm__model__layers__61__self_attn__q_proj__weight", "model.layers.61.self_attn.k_proj.weight": "llamaforcausallm__model__layers__61__self_attn__k_proj__weight", "model.layers.61.self_attn.v_proj.weight": "llamaforcausallm__model__layers__61__self_attn__v_proj__weight", "model.layers.61.self_attn.o_proj.weight": "llamaforcausallm__model__layers__61__self_attn__o_proj__weight", "model.layers.61.mlp.gate_proj.weight": "llamaforcausallm__model__layers__61__mlp__gate_proj__weight", "model.layers.61.mlp.up_proj.weight": "llamaforcausallm__model__layers__61__mlp__up_proj__weight", "model.layers.61.mlp.down_proj.weight": "llamaforcausallm__model__layers__61__mlp__down_proj__weight", "model.layers.61.input_layernorm.weight": "llamaforcausallm__model__layers__61__input_layernorm__weight", "model.layers.61.post_attention_layernorm.weight": "llamaforcausallm__model__layers__61__post_attention_layernorm__weight", "model.layers.62.self_attn.q_proj.weight": "llamaforcausallm__model__layers__62__self_attn__q_proj__weight", "model.layers.62.self_attn.k_proj.weight": "llamaforcausallm__model__layers__62__self_attn__k_proj__weight", "model.layers.62.self_attn.v_proj.weight": "llamaforcausallm__model__layers__62__self_attn__v_proj__weight", "model.layers.62.self_attn.o_proj.weight": "llamaforcausallm__model__layers__62__self_attn__o_proj__weight", "model.layers.62.mlp.gate_proj.weight": "llamaforcausallm__model__layers__62__mlp__gate_proj__weight", "model.layers.62.mlp.up_proj.weight": "llamaforcausallm__model__layers__62__mlp__up_proj__weight", "model.layers.62.mlp.down_proj.weight": "llamaforcausallm__model__layers__62__mlp__down_proj__weight", "model.layers.62.input_layernorm.weight": "llamaforcausallm__model__layers__62__input_layernorm__weight", "model.layers.62.post_attention_layernorm.weight": "llamaforcausallm__model__layers__62__post_attention_layernorm__weight", "model.layers.63.self_attn.q_proj.weight": "llamaforcausallm__model__layers__63__self_attn__q_proj__weight", "model.layers.63.self_attn.k_proj.weight": "llamaforcausallm__model__layers__63__self_attn__k_proj__weight", "model.layers.63.self_attn.v_proj.weight": "llamaforcausallm__model__layers__63__self_attn__v_proj__weight", "model.layers.63.self_attn.o_proj.weight": "llamaforcausallm__model__layers__63__self_attn__o_proj__weight", "model.layers.63.mlp.gate_proj.weight": "llamaforcausallm__model__layers__63__mlp__gate_proj__weight", "model.layers.63.mlp.up_proj.weight": "llamaforcausallm__model__layers__63__mlp__up_proj__weight", "model.layers.63.mlp.down_proj.weight": "llamaforcausallm__model__layers__63__mlp__down_proj__weight", "model.layers.63.input_layernorm.weight": "llamaforcausallm__model__layers__63__input_layernorm__weight", "model.layers.63.post_attention_layernorm.weight": "llamaforcausallm__model__layers__63__post_attention_layernorm__weight", "model.layers.64.self_attn.q_proj.weight": "llamaforcausallm__model__layers__64__self_attn__q_proj__weight", "model.layers.64.self_attn.k_proj.weight": "llamaforcausallm__model__layers__64__self_attn__k_proj__weight", "model.layers.64.self_attn.v_proj.weight": "llamaforcausallm__model__layers__64__self_attn__v_proj__weight", "model.layers.64.self_attn.o_proj.weight": "llamaforcausallm__model__layers__64__self_attn__o_proj__weight", "model.layers.64.mlp.gate_proj.weight": "llamaforcausallm__model__layers__64__mlp__gate_proj__weight", "model.layers.64.mlp.up_proj.weight": "llamaforcausallm__model__layers__64__mlp__up_proj__weight", "model.layers.64.mlp.down_proj.weight": "llamaforcausallm__model__layers__64__mlp__down_proj__weight", "model.layers.64.input_layernorm.weight": "llamaforcausallm__model__layers__64__input_layernorm__weight", "model.layers.64.post_attention_layernorm.weight": "llamaforcausallm__model__layers__64__post_attention_layernorm__weight", "model.layers.65.self_attn.q_proj.weight": "llamaforcausallm__model__layers__65__self_attn__q_proj__weight", "model.layers.65.self_attn.k_proj.weight": "llamaforcausallm__model__layers__65__self_attn__k_proj__weight", "model.layers.65.self_attn.v_proj.weight": "llamaforcausallm__model__layers__65__self_attn__v_proj__weight", "model.layers.65.self_attn.o_proj.weight": "llamaforcausallm__model__layers__65__self_attn__o_proj__weight", "model.layers.65.mlp.gate_proj.weight": "llamaforcausallm__model__layers__65__mlp__gate_proj__weight", "model.layers.65.mlp.up_proj.weight": "llamaforcausallm__model__layers__65__mlp__up_proj__weight", "model.layers.65.mlp.down_proj.weight": "llamaforcausallm__model__layers__65__mlp__down_proj__weight", "model.layers.65.input_layernorm.weight": "llamaforcausallm__model__layers__65__input_layernorm__weight", "model.layers.65.post_attention_layernorm.weight": "llamaforcausallm__model__layers__65__post_attention_layernorm__weight", "model.layers.66.self_attn.q_proj.weight": "llamaforcausallm__model__layers__66__self_attn__q_proj__weight", "model.layers.66.self_attn.k_proj.weight": "llamaforcausallm__model__layers__66__self_attn__k_proj__weight", "model.layers.66.self_attn.v_proj.weight": "llamaforcausallm__model__layers__66__self_attn__v_proj__weight", "model.layers.66.self_attn.o_proj.weight": "llamaforcausallm__model__layers__66__self_attn__o_proj__weight", "model.layers.66.mlp.gate_proj.weight": "llamaforcausallm__model__layers__66__mlp__gate_proj__weight", "model.layers.66.mlp.up_proj.weight": "llamaforcausallm__model__layers__66__mlp__up_proj__weight", "model.layers.66.mlp.down_proj.weight": "llamaforcausallm__model__layers__66__mlp__down_proj__weight", "model.layers.66.input_layernorm.weight": "llamaforcausallm__model__layers__66__input_layernorm__weight", "model.layers.66.post_attention_layernorm.weight": "llamaforcausallm__model__layers__66__post_attention_layernorm__weight", "model.layers.67.self_attn.q_proj.weight": "llamaforcausallm__model__layers__67__self_attn__q_proj__weight", "model.layers.67.self_attn.k_proj.weight": "llamaforcausallm__model__layers__67__self_attn__k_proj__weight", "model.layers.67.self_attn.v_proj.weight": "llamaforcausallm__model__layers__67__self_attn__v_proj__weight", "model.layers.67.self_attn.o_proj.weight": "llamaforcausallm__model__layers__67__self_attn__o_proj__weight", "model.layers.67.mlp.gate_proj.weight": "llamaforcausallm__model__layers__67__mlp__gate_proj__weight", "model.layers.67.mlp.up_proj.weight": "llamaforcausallm__model__layers__67__mlp__up_proj__weight", "model.layers.67.mlp.down_proj.weight": "llamaforcausallm__model__layers__67__mlp__down_proj__weight", "model.layers.67.input_layernorm.weight": "llamaforcausallm__model__layers__67__input_layernorm__weight", "model.layers.67.post_attention_layernorm.weight": "llamaforcausallm__model__layers__67__post_attention_layernorm__weight", "model.layers.68.self_attn.q_proj.weight": "llamaforcausallm__model__layers__68__self_attn__q_proj__weight", "model.layers.68.self_attn.k_proj.weight": "llamaforcausallm__model__layers__68__self_attn__k_proj__weight", "model.layers.68.self_attn.v_proj.weight": "llamaforcausallm__model__layers__68__self_attn__v_proj__weight", "model.layers.68.self_attn.o_proj.weight": "llamaforcausallm__model__layers__68__self_attn__o_proj__weight", "model.layers.68.mlp.gate_proj.weight": "llamaforcausallm__model__layers__68__mlp__gate_proj__weight", "model.layers.68.mlp.up_proj.weight": "llamaforcausallm__model__layers__68__mlp__up_proj__weight", "model.layers.68.mlp.down_proj.weight": "llamaforcausallm__model__layers__68__mlp__down_proj__weight", "model.layers.68.input_layernorm.weight": "llamaforcausallm__model__layers__68__input_layernorm__weight", "model.layers.68.post_attention_layernorm.weight": "llamaforcausallm__model__layers__68__post_attention_layernorm__weight", "model.layers.69.self_attn.q_proj.weight": "llamaforcausallm__model__layers__69__self_attn__q_proj__weight", "model.layers.69.self_attn.k_proj.weight": "llamaforcausallm__model__layers__69__self_attn__k_proj__weight", "model.layers.69.self_attn.v_proj.weight": "llamaforcausallm__model__layers__69__self_attn__v_proj__weight", "model.layers.69.self_attn.o_proj.weight": "llamaforcausallm__model__layers__69__self_attn__o_proj__weight", "model.layers.69.mlp.gate_proj.weight": "llamaforcausallm__model__layers__69__mlp__gate_proj__weight", "model.layers.69.mlp.up_proj.weight": "llamaforcausallm__model__layers__69__mlp__up_proj__weight", "model.layers.69.mlp.down_proj.weight": "llamaforcausallm__model__layers__69__mlp__down_proj__weight", "model.layers.69.input_layernorm.weight": "llamaforcausallm__model__layers__69__input_layernorm__weight", "model.layers.69.post_attention_layernorm.weight": "llamaforcausallm__model__layers__69__post_attention_layernorm__weight", "model.layers.70.self_attn.q_proj.weight": "llamaforcausallm__model__layers__70__self_attn__q_proj__weight", "model.layers.70.self_attn.k_proj.weight": "llamaforcausallm__model__layers__70__self_attn__k_proj__weight", "model.layers.70.self_attn.v_proj.weight": "llamaforcausallm__model__layers__70__self_attn__v_proj__weight", "model.layers.70.self_attn.o_proj.weight": "llamaforcausallm__model__layers__70__self_attn__o_proj__weight", "model.layers.70.mlp.gate_proj.weight": "llamaforcausallm__model__layers__70__mlp__gate_proj__weight", "model.layers.70.mlp.up_proj.weight": "llamaforcausallm__model__layers__70__mlp__up_proj__weight", "model.layers.70.mlp.down_proj.weight": "llamaforcausallm__model__layers__70__mlp__down_proj__weight", "model.layers.70.input_layernorm.weight": "llamaforcausallm__model__layers__70__input_layernorm__weight", "model.layers.70.post_attention_layernorm.weight": "llamaforcausallm__model__layers__70__post_attention_layernorm__weight", "model.layers.71.self_attn.q_proj.weight": "llamaforcausallm__model__layers__71__self_attn__q_proj__weight", "model.layers.71.self_attn.k_proj.weight": "llamaforcausallm__model__layers__71__self_attn__k_proj__weight", "model.layers.71.self_attn.v_proj.weight": "llamaforcausallm__model__layers__71__self_attn__v_proj__weight", "model.layers.71.self_attn.o_proj.weight": "llamaforcausallm__model__layers__71__self_attn__o_proj__weight", "model.layers.71.mlp.gate_proj.weight": "llamaforcausallm__model__layers__71__mlp__gate_proj__weight", "model.layers.71.mlp.up_proj.weight": "llamaforcausallm__model__layers__71__mlp__up_proj__weight", "model.layers.71.mlp.down_proj.weight": "llamaforcausallm__model__layers__71__mlp__down_proj__weight", "model.layers.71.input_layernorm.weight": "llamaforcausallm__model__layers__71__input_layernorm__weight", "model.layers.71.post_attention_layernorm.weight": "llamaforcausallm__model__layers__71__post_attention_layernorm__weight", "model.layers.72.self_attn.q_proj.weight": "llamaforcausallm__model__layers__72__self_attn__q_proj__weight", "model.layers.72.self_attn.k_proj.weight": "llamaforcausallm__model__layers__72__self_attn__k_proj__weight", "model.layers.72.self_attn.v_proj.weight": "llamaforcausallm__model__layers__72__self_attn__v_proj__weight", "model.layers.72.self_attn.o_proj.weight": "llamaforcausallm__model__layers__72__self_attn__o_proj__weight", "model.layers.72.mlp.gate_proj.weight": "llamaforcausallm__model__layers__72__mlp__gate_proj__weight", "model.layers.72.mlp.up_proj.weight": "llamaforcausallm__model__layers__72__mlp__up_proj__weight", "model.layers.72.mlp.down_proj.weight": "llamaforcausallm__model__layers__72__mlp__down_proj__weight", "model.layers.72.input_layernorm.weight": "llamaforcausallm__model__layers__72__input_layernorm__weight", "model.layers.72.post_attention_layernorm.weight": "llamaforcausallm__model__layers__72__post_attention_layernorm__weight", "model.layers.73.self_attn.q_proj.weight": "llamaforcausallm__model__layers__73__self_attn__q_proj__weight", "model.layers.73.self_attn.k_proj.weight": "llamaforcausallm__model__layers__73__self_attn__k_proj__weight", "model.layers.73.self_attn.v_proj.weight": "llamaforcausallm__model__layers__73__self_attn__v_proj__weight", "model.layers.73.self_attn.o_proj.weight": "llamaforcausallm__model__layers__73__self_attn__o_proj__weight", "model.layers.73.mlp.gate_proj.weight": "llamaforcausallm__model__layers__73__mlp__gate_proj__weight", "model.layers.73.mlp.up_proj.weight": "llamaforcausallm__model__layers__73__mlp__up_proj__weight", "model.layers.73.mlp.down_proj.weight": "llamaforcausallm__model__layers__73__mlp__down_proj__weight", "model.layers.73.input_layernorm.weight": "llamaforcausallm__model__layers__73__input_layernorm__weight", "model.layers.73.post_attention_layernorm.weight": "llamaforcausallm__model__layers__73__post_attention_layernorm__weight", "model.layers.74.self_attn.q_proj.weight": "llamaforcausallm__model__layers__74__self_attn__q_proj__weight", "model.layers.74.self_attn.k_proj.weight": "llamaforcausallm__model__layers__74__self_attn__k_proj__weight", "model.layers.74.self_attn.v_proj.weight": "llamaforcausallm__model__layers__74__self_attn__v_proj__weight", "model.layers.74.self_attn.o_proj.weight": "llamaforcausallm__model__layers__74__self_attn__o_proj__weight", "model.layers.74.mlp.gate_proj.weight": "llamaforcausallm__model__layers__74__mlp__gate_proj__weight", "model.layers.74.mlp.up_proj.weight": "llamaforcausallm__model__layers__74__mlp__up_proj__weight", "model.layers.74.mlp.down_proj.weight": "llamaforcausallm__model__layers__74__mlp__down_proj__weight", "model.layers.74.input_layernorm.weight": "llamaforcausallm__model__layers__74__input_layernorm__weight", "model.layers.74.post_attention_layernorm.weight": "llamaforcausallm__model__layers__74__post_attention_layernorm__weight", "model.layers.75.self_attn.q_proj.weight": "llamaforcausallm__model__layers__75__self_attn__q_proj__weight", "model.layers.75.self_attn.k_proj.weight": "llamaforcausallm__model__layers__75__self_attn__k_proj__weight", "model.layers.75.self_attn.v_proj.weight": "llamaforcausallm__model__layers__75__self_attn__v_proj__weight", "model.layers.75.self_attn.o_proj.weight": "llamaforcausallm__model__layers__75__self_attn__o_proj__weight", "model.layers.75.mlp.gate_proj.weight": "llamaforcausallm__model__layers__75__mlp__gate_proj__weight", "model.layers.75.mlp.up_proj.weight": "llamaforcausallm__model__layers__75__mlp__up_proj__weight", "model.layers.75.mlp.down_proj.weight": "llamaforcausallm__model__layers__75__mlp__down_proj__weight", "model.layers.75.input_layernorm.weight": "llamaforcausallm__model__layers__75__input_layernorm__weight", "model.layers.75.post_attention_layernorm.weight": "llamaforcausallm__model__layers__75__post_attention_layernorm__weight", "model.layers.76.self_attn.q_proj.weight": "llamaforcausallm__model__layers__76__self_attn__q_proj__weight", "model.layers.76.self_attn.k_proj.weight": "llamaforcausallm__model__layers__76__self_attn__k_proj__weight", "model.layers.76.self_attn.v_proj.weight": "llamaforcausallm__model__layers__76__self_attn__v_proj__weight", "model.layers.76.self_attn.o_proj.weight": "llamaforcausallm__model__layers__76__self_attn__o_proj__weight", "model.layers.76.mlp.gate_proj.weight": "llamaforcausallm__model__layers__76__mlp__gate_proj__weight", "model.layers.76.mlp.up_proj.weight": "llamaforcausallm__model__layers__76__mlp__up_proj__weight", "model.layers.76.mlp.down_proj.weight": "llamaforcausallm__model__layers__76__mlp__down_proj__weight", "model.layers.76.input_layernorm.weight": "llamaforcausallm__model__layers__76__input_layernorm__weight", "model.layers.76.post_attention_layernorm.weight": "llamaforcausallm__model__layers__76__post_attention_layernorm__weight", "model.layers.77.self_attn.q_proj.weight": "llamaforcausallm__model__layers__77__self_attn__q_proj__weight", "model.layers.77.self_attn.k_proj.weight": "llamaforcausallm__model__layers__77__self_attn__k_proj__weight", "model.layers.77.self_attn.v_proj.weight": "llamaforcausallm__model__layers__77__self_attn__v_proj__weight", "model.layers.77.self_attn.o_proj.weight": "llamaforcausallm__model__layers__77__self_attn__o_proj__weight", "model.layers.77.mlp.gate_proj.weight": "llamaforcausallm__model__layers__77__mlp__gate_proj__weight", "model.layers.77.mlp.up_proj.weight": "llamaforcausallm__model__layers__77__mlp__up_proj__weight", "model.layers.77.mlp.down_proj.weight": "llamaforcausallm__model__layers__77__mlp__down_proj__weight", "model.layers.77.input_layernorm.weight": "llamaforcausallm__model__layers__77__input_layernorm__weight", "model.layers.77.post_attention_layernorm.weight": "llamaforcausallm__model__layers__77__post_attention_layernorm__weight", "model.layers.78.self_attn.q_proj.weight": "llamaforcausallm__model__layers__78__self_attn__q_proj__weight", "model.layers.78.self_attn.k_proj.weight": "llamaforcausallm__model__layers__78__self_attn__k_proj__weight", "model.layers.78.self_attn.v_proj.weight": "llamaforcausallm__model__layers__78__self_attn__v_proj__weight", "model.layers.78.self_attn.o_proj.weight": "llamaforcausallm__model__layers__78__self_attn__o_proj__weight", "model.layers.78.mlp.gate_proj.weight": "llamaforcausallm__model__layers__78__mlp__gate_proj__weight", "model.layers.78.mlp.up_proj.weight": "llamaforcausallm__model__layers__78__mlp__up_proj__weight", "model.layers.78.mlp.down_proj.weight": "llamaforcausallm__model__layers__78__mlp__down_proj__weight", "model.layers.78.input_layernorm.weight": "llamaforcausallm__model__layers__78__input_layernorm__weight", "model.layers.78.post_attention_layernorm.weight": "llamaforcausallm__model__layers__78__post_attention_layernorm__weight", "model.layers.79.self_attn.q_proj.weight": "llamaforcausallm__model__layers__79__self_attn__q_proj__weight", "model.layers.79.self_attn.k_proj.weight": "llamaforcausallm__model__layers__79__self_attn__k_proj__weight", "model.layers.79.self_attn.v_proj.weight": "llamaforcausallm__model__layers__79__self_attn__v_proj__weight", "model.layers.79.self_attn.o_proj.weight": "llamaforcausallm__model__layers__79__self_attn__o_proj__weight", "model.layers.79.mlp.gate_proj.weight": "llamaforcausallm__model__layers__79__mlp__gate_proj__weight", "model.layers.79.mlp.up_proj.weight": "llamaforcausallm__model__layers__79__mlp__up_proj__weight", "model.layers.79.mlp.down_proj.weight": "llamaforcausallm__model__layers__79__mlp__down_proj__weight", "model.layers.79.input_layernorm.weight": "llamaforcausallm__model__layers__79__input_layernorm__weight", "model.layers.79.post_attention_layernorm.weight": "llamaforcausallm__model__layers__79__post_attention_layernorm__weight", "model.norm.weight": "llamaforcausallm__model__norm__weight", "lm_head.weight": "llamaforcausallm__lm_head__weight"}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e358066070e28277acbdf4ff778b22f285ba9b61a92668e7f54307882967ec1
3
+ size 986150
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }