Hugging Face's logo

Rombo-Org
/
Rombo-LLM-V2.5-Qwen-72b

Text Generation
Transformers
Safetensors
qwen2
conversational
Eval Results
text-generation-inference
Model card Files
xet
Community
1
rombodawg commited on
Commit
148d2a1
·
verified ·
0 Parent(s):

Duplicate from rombodawg/Rombos-LLM-V2.5-Qwen-72b

Browse files
Files changed (40) hide show
  1. .gitattributes +31 -0
  2. README.md +132 -0
  3. config.json +27 -0
  4. generation_config.json +14 -0
  5. mergekit_config.yml +10 -0
  6. model-00001-of-00031.safetensors +3 -0
  7. model-00002-of-00031.safetensors +3 -0
  8. model-00003-of-00031.safetensors +3 -0
  9. model-00004-of-00031.safetensors +3 -0
  10. model-00005-of-00031.safetensors +3 -0
  11. model-00006-of-00031.safetensors +3 -0
  12. model-00007-of-00031.safetensors +3 -0
  13. model-00008-of-00031.safetensors +3 -0
  14. model-00009-of-00031.safetensors +3 -0
  15. model-00010-of-00031.safetensors +3 -0
  16. model-00011-of-00031.safetensors +3 -0
  17. model-00012-of-00031.safetensors +3 -0
  18. model-00013-of-00031.safetensors +3 -0
  19. model-00014-of-00031.safetensors +3 -0
  20. model-00015-of-00031.safetensors +3 -0
  21. model-00016-of-00031.safetensors +3 -0
  22. model-00017-of-00031.safetensors +3 -0
  23. model-00018-of-00031.safetensors +3 -0
  24. model-00019-of-00031.safetensors +3 -0
  25. model-00020-of-00031.safetensors +3 -0
  26. model-00021-of-00031.safetensors +3 -0
  27. model-00022-of-00031.safetensors +3 -0
  28. model-00023-of-00031.safetensors +3 -0
  29. model-00024-of-00031.safetensors +3 -0
  30. model-00025-of-00031.safetensors +3 -0
  31. model-00026-of-00031.safetensors +3 -0
  32. model-00027-of-00031.safetensors +3 -0
  33. model-00028-of-00031.safetensors +3 -0
  34. model-00029-of-00031.safetensors +3 -0
  35. model-00030-of-00031.safetensors +3 -0
  36. model-00031-of-00031.safetensors +3 -0
  37. model.safetensors.index.json +1 -0
  38. tokenizer.json +0 -0
  39. tokenizer_config.json +207 -0
  40. vocab.json +0 -0
.gitattributes ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model-00010-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
2
+ model-00019-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
3
+ model-00013-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
4
+ model-00024-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
5
+ model-00023-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
6
+ model-00017-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
7
+ model-00009-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
8
+ model-00003-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
9
+ model-00005-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
10
+ model-00006-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
11
+ model-00004-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
12
+ model-00018-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
13
+ model-00012-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
14
+ model-00002-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
15
+ model-00011-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
16
+ model-00014-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
17
+ model-00030-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
18
+ model-00029-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
19
+ model-00031-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
20
+ model-00026-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
21
+ model-00001-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
22
+ model-00007-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
23
+ model-00020-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
24
+ model-00022-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
25
+ model-00027-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ model-00028-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
27
+ model-00025-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
28
+ model-00008-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
29
+ model-00016-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
30
+ model-00021-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
31
+ model-00015-of-00031.safetensors filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: transformers
4
+ base_model:
5
+ - Qwen/Qwen2.5-72B-Instruct
6
+ license_name: qwen
7
+ license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
8
+ model-index:
9
+ - name: Replete-LLM-V2.5-Qwen-72b_Duplicated
10
+ results:
11
+ - task:
12
+ type: text-generation
13
+ name: Text Generation
14
+ dataset:
15
+ name: IFEval (0-Shot)
16
+ type: HuggingFaceH4/ifeval
17
+ args:
18
+ num_few_shot: 0
19
+ metrics:
20
+ - type: inst_level_strict_acc and prompt_level_strict_acc
21
+ value: 71.55
22
+ name: strict accuracy
23
+ source:
24
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
25
+ name: Open LLM Leaderboard
26
+ - task:
27
+ type: text-generation
28
+ name: Text Generation
29
+ dataset:
30
+ name: BBH (3-Shot)
31
+ type: BBH
32
+ args:
33
+ num_few_shot: 3
34
+ metrics:
35
+ - type: acc_norm
36
+ value: 61.27
37
+ name: normalized accuracy
38
+ source:
39
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
40
+ name: Open LLM Leaderboard
41
+ - task:
42
+ type: text-generation
43
+ name: Text Generation
44
+ dataset:
45
+ name: MATH Lvl 5 (4-Shot)
46
+ type: hendrycks/competition_math
47
+ args:
48
+ num_few_shot: 4
49
+ metrics:
50
+ - type: exact_match
51
+ value: 47.58
52
+ name: exact match
53
+ source:
54
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
55
+ name: Open LLM Leaderboard
56
+ - task:
57
+ type: text-generation
58
+ name: Text Generation
59
+ dataset:
60
+ name: GPQA (0-shot)
61
+ type: Idavidrein/gpqa
62
+ args:
63
+ num_few_shot: 0
64
+ metrics:
65
+ - type: acc_norm
66
+ value: 19.8
67
+ name: acc_norm
68
+ source:
69
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
70
+ name: Open LLM Leaderboard
71
+ - task:
72
+ type: text-generation
73
+ name: Text Generation
74
+ dataset:
75
+ name: MuSR (0-shot)
76
+ type: TAUR-Lab/MuSR
77
+ args:
78
+ num_few_shot: 0
79
+ metrics:
80
+ - type: acc_norm
81
+ value: 17.32
82
+ name: acc_norm
83
+ source:
84
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
85
+ name: Open LLM Leaderboard
86
+ - task:
87
+ type: text-generation
88
+ name: Text Generation
89
+ dataset:
90
+ name: MMLU-PRO (5-shot)
91
+ type: TIGER-Lab/MMLU-Pro
92
+ config: main
93
+ split: test
94
+ args:
95
+ num_few_shot: 5
96
+ metrics:
97
+ - type: acc
98
+ value: 54.83
99
+ name: accuracy
100
+ source:
101
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Replete-LLM-V2.5-Qwen-72b_Duplicated
102
+ name: Open LLM Leaderboard
103
+ ---
104
+ # Rombos-LLM-V2.5-Qwen-72b
105
+
106
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/wp9qOi2K2WGzkey0I3SgH.jpeg)
107
+
108
+ Rombos-LLM-V2.5-Qwen-72b is a continues finetuned version of Qwen2.5-72B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the *Ties* merge method
109
+
110
+ This version of the model shows higher performance than the original instruct and base models.
111
+
112
+ Quants: (Coming soon)
113
+
114
+ GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-72b-GGUF
115
+
116
+ EXL2:
117
+
118
+ Benchmarks: (Coming soon)
119
+
120
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
121
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rombodawg__Replete-LLM-V2.5-Qwen-72b_Duplicated)
122
+
123
+ | Metric |Value|
124
+ |-------------------|----:|
125
+ |Avg. |45.39|
126
+ |IFEval (0-Shot) |71.55|
127
+ |BBH (3-Shot) |61.27|
128
+ |MATH Lvl 5 (4-Shot)|47.58|
129
+ |GPQA (0-shot) |19.80|
130
+ |MuSR (0-shot) |17.32|
131
+ |MMLU-PRO (5-shot) |54.83|
132
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 29568,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 70,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 152064
27
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "pad_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_p": 0.8,
12
+ "top_k": 20,
13
+ "transformers_version": "4.37.0"
14
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: ./qwen-72b-instruct
3
+ parameters:
4
+ weight: 1
5
+ merge_method: ties
6
+ base_model: ./qwen-72b
7
+ parameters:
8
+ normalize: true
9
+ int8_mask: true
10
+ dtype: bfloat16
model-00001-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb06a5f277e45a9f8aa821f8aa8f7bb46fd75a975cf3ff5cd65bc9cdf539039
3
+ size 4982849880
model-00002-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19173c618434d4c12c044c1be055a549f579dad53364cd3e4b232811cc1d7b7c
3
+ size 4980864400
model-00003-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aebb1c224917afef05bb64fb252b19c66f524005af9601e114cc974af75253fa
3
+ size 4764874368
model-00004-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f8011fc093c26bd985e091de52a5bbfac3ee8ecd5017d1b8e0ed97216c87fe
3
+ size 4781670352
model-00005-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04845e18515262ba7d8bc69b342a978c45c66b6fce363526de1d2d7c51a4101
3
+ size 4781670368
model-00006-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa27335005b100229eb6e6e0dcef4a9042879aa4dcd8f7188d24a125cc340104
3
+ size 4980864408
model-00007-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74883c01cdd36e7089129fdca50dd3c9dd5c7d3cc17b3ca52aa8bf776ee4361e
3
+ size 4764874368
model-00008-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dbd3b8d8465283f3ecb38afad72b1e7b310acbfa5658191d57067b0b1c37ebe
3
+ size 4781670352
model-00009-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a1d325439b794428b7f09a9c5b75e74430640b89f5604a8a3ccf7044acb2c2
3
+ size 4781670368
model-00010-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8526047e4816c0e1aa8a2346ce2ee37a353536bf5d3bc39344245cc2f05bd0da
3
+ size 4980864408
model-00011-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5314b31451e1d053e0a6b729dbe521827b3faf31709e5677959e2668dd3a830
3
+ size 4764874368
model-00012-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ddaf1ec0d6d0fcc7f38cc2f634e61cc4070c7b5caf9744b109689ba246df7b
3
+ size 4781670352
model-00013-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97af705dfa1b408b6174502a34f1a574b6db41e87892dfaa1501254880bbdf40
3
+ size 4781670368
model-00014-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adafd74a9686eb1942831a6fa7fe52ff89c0cde1b3f37d86ac4eb0054f76f533
3
+ size 4980864408
model-00015-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feda7248706e5ea6cad3541574a86ae5e000f9549969bf13f477ed267ea1b191
3
+ size 4764874368
model-00016-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22474d623a802bb8ce22c9920a7231e1d0d1096cae9e6ec178dbdd31c47ab64
3
+ size 4781670352
model-00017-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecb9ea7e88dbdc5e6076120bb887cd0755442986222a57413fdd99d602d6434
3
+ size 4781670368
model-00018-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47be311e93ca601b51a5c528dc169211c76a9648cc601f797904d380c15ebb55
3
+ size 4980864408
model-00019-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b753e9f4ce3180d54dd1b3c7aede00b069b0dceb0090fe6aa096b0175c49b517
3
+ size 4764874368
model-00020-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9246462b51a16baf484d29b46c04501c330859b7ce3901e39564e320ca7db6
3
+ size 4781670352
model-00021-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:735c70eff7b2be326630a511aac1aa0c1240f0e9e94db16879bf7c4ef9b61ed0
3
+ size 4781670368
model-00022-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59236be0df97c350be6c6c3e0f98e3a54d6f76a3e698272cfffd5271b8f65e07
3
+ size 4980864408
model-00023-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8dcf98be68e8df90628eb4b7503e1fa2c621178eae28c72f248c9d4e3828995
3
+ size 4764874368
model-00024-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b538e7146509a78445362857657b3529c91bba0bcca3b8478714914ac09c53
3
+ size 4781670352
model-00025-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d2d5be585de95057c6f38e024a402324dabbc89a5f0bec75f1885667528296
3
+ size 4781670368
model-00026-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ae7fe7454e1b1d1a4fb35865412c3ed1b25329ddf8d26ed8ca008425ab1192
3
+ size 4980864408
model-00027-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2768653ebeeaa164da38f68b4cddebc2ec242a9cbda13a8060754c14c03918c6
3
+ size 4764874368
model-00028-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75c61feb531f0fc18295d5c7b1edca1c371068eda2bbddf2fe9bdd3e681df63
3
+ size 4781670352
model-00029-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0592ca3d1f14a6f273765c9f58396884e94c84762ba8ef0cd95924389bad27d
3
+ size 4781670368
model-00030-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb382f0038e5934eac489deae43e0041ce6f142ccfdc40f082e1b20a80761393
3
+ size 4980864400
model-00031-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59621b3c71bff1ca45783b64cbfc99887d76bd63664477669607395f944e7f7
3
+ size 285248176
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 145412407296}, "weight_map": {"lm_head.weight": "model-00001-of-00031.safetensors", "model.embed_tokens.weight": "model-00001-of-00031.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00031.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00031.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00031.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00031.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00031.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00031.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00031.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00031.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00031.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00031.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00031.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00031.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00031.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00031.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00031.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00031.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00031.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00031.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00031.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00031.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00031.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00031.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00031.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00031.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00031.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00031.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00031.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00031.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00031.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00031.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00031.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00031.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00031.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00031.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00031.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00031.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00031.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00031.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00031.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00031.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00031.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00031.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00031.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00031.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00031.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00031.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00031.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00031.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00031.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00031.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00031.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00031.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00031.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00031.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00031.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00031.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00031.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00031.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00031.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00031.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00031.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00031-of-00031.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00031-of-00031.safetensors", "model.norm.weight": "model-00031-of-00031.safetensors"}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff