[WIP] Upload folder using huggingface_hub (multi-commit be7b2e993a25946bc4eed61be65cc5e5c06d4711088ce0f869def2e13e099da8)

#2
README.md DELETED
@@ -1,58 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - zh
5
- - en
6
- metrics:
7
- - accuracy
8
- pipeline_tag: text-generation
9
- tags:
10
- - chat
11
- - evaluate
12
- ---
13
- # flageval_judgemodel Card
14
-
15
- ## Model Details
16
-
17
- flageval_judgemodel is a judgeLLM developed by FlagEval team (https://flageval.baai.ac.cn/#/home).
18
-
19
- - **Developed by:** [FlagEval](https://flageval.baai.ac.cn/#/home), [BAAI](https://www.baai.ac.cn/english.html)
20
- - **Model type:** An auto-regressive language model based on the transformer architecture.
21
- - **License:** Non-commercial license
22
- - **Finetuned from model:** [Vicuna](https://vicuna.lmsys.org).
23
-
24
- ## Uses
25
-
26
- The flageval_judgemodel is designed to evaluate the performance of large language models on CLCC dataset. This dataset (https://huggingface.co/datasets/eyuansu71/CLCC_v1) is a Chinese Linguistics & Cognition Challenge dataset. The flageval_judgemodel aims to provide an automated evaluation, potentially replacing human judgment in assessing the models' outputs.
27
-
28
-
29
- ## Quickstart
30
-
31
-
32
- ```python
33
- import torch
34
- from transformers import AutoModelForCausalLM, AutoTokenizer
35
-
36
- def promptify(prompt, pred, gold):
37
- sys = "We would like to request your feedback on the performance of two AI assistants in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only two values indicating the scores for Assistant 1 and 2, respectively. The two scores are separated by a space. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment."
38
- prompt_template = f"You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\n{prompt}\n\n[The Start of Assistant 1's Answer]\n{gold}\n\n[The End of Assistant 1's Answer]\n\n[The Start of Assistant 2's Answer]\n{pred}\n\n[The End of Assistant 2's Answer]\n\n[System]\n{sys}\n\n### Response:10"
39
-
40
- return prompt_template
41
-
42
- model = AutoModelForCausalLM.from_pretrained("FlagEval/flageval_judgemodel", torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, attn_implementation="flash_attention_2").cuda()
43
- tokenizer = AutoTokenizer.from_pretrained("FlagEval/flageval_judgemodel")
44
-
45
- prompt, pred, gold = '1、约翰喜欢看电影,玛丽也喜欢。\n2、约翰也喜欢看足球比赛。\n请问以上两句话是否是一个意思?', "不一样", "不一样"
46
-
47
- with torch.no_grad():
48
- data_sample = promptify(prompt, pred, gold)
49
- input_ids = tokenizer(data_sample, return_tensors="pt").input_ids
50
- output_ids = model.generate(
51
- torch.as_tensor(input_ids).cuda(),
52
- max_new_tokens=128,
53
- )
54
- text = tokenizer.decode(output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
55
- prompt_length = len(data_sample)
56
- ans = text[prompt_length:].strip()
57
- pred_label = 1 if int(ans) == 10 else 0
58
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,10 +1,8 @@
1
  {
2
- "_name_or_path": "/home/qinbowen/llm_judge/aquila_judge/JudgeLM/judgelm/output/judgelm-debug-evaluator-v12/checkpoint-460",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
@@ -20,10 +18,9 @@
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-06,
22
  "rope_scaling": null,
23
- "rope_theta": 10000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.40.0",
27
  "use_cache": false,
28
  "vocab_size": 32000
29
  }
 
1
  {
2
+ "_name_or_path": "/home/qinbowen/models/judgelm33b/1",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
 
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
 
18
  "pretraining_tp": 1,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.32.0",
24
  "use_cache": false,
25
  "vocab_size": 32000
26
  }
generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.40.0"
7
- }
 
 
 
 
 
 
 
 
model-00001-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b9aacdcb8d0defda17854f98c582c1b640b839472a6c2cdceb0b5840c439e4
3
- size 9818301384
 
 
 
 
model-00002-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ade9f2402613f1d9e11ded549b93856aa8fd15c09387985fd38bd14f65f5cb3
3
- size 9958078152
 
 
 
 
model-00003-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7afae70e9c79427af0e29f5f167152b307ca4cda9491dddfeebe80eaf0363b7
3
- size 9896709728
 
 
 
 
model-00004-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:083cb0fa678bb94b5af6fd8d13fba6cc38057669ea99d8484761205d1633606a
3
- size 9869446512
 
 
 
 
model-00005-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:abd55c7b341ec74443dfb41b5f25c4b7b289a1016a9230f3d5a008e2e96b243d
3
- size 9869446512
 
 
 
 
model-00006-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fcab592ff5c3c49794e0a029e5eed73bb92832324af5e3d9f68950f619ec1a2
3
- size 9958078160
 
 
 
 
model-00007-of-00007.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1cbb965d018a4e4d671a8a023887a4abe1452f459afc8d454194e730d0f7c42
3
- size 5687890152
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,550 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 65057887232
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00007-of-00007.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
242
- "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
243
- "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
244
- "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
245
- "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
246
- "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
247
- "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
248
- "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
249
- "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
250
- "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
251
- "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
252
- "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
253
- "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
254
- "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
255
- "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
256
- "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
257
- "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
258
- "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
259
- "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
260
- "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
261
- "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
262
- "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
263
- "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
264
- "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
265
- "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
266
- "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
267
- "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
268
- "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
269
- "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
270
- "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
271
- "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
272
- "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
273
- "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
274
- "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
275
- "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
276
- "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
277
- "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
278
- "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
279
- "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
280
- "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
281
- "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
282
- "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
283
- "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
284
- "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
285
- "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
286
- "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
287
- "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
288
- "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
289
- "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
290
- "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
291
- "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
292
- "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
293
- "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
294
- "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
295
- "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
296
- "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
297
- "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
298
- "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
299
- "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
300
- "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
301
- "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
302
- "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
303
- "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
304
- "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
305
- "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
306
- "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
307
- "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
308
- "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
309
- "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
310
- "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
311
- "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
312
- "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
313
- "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
314
- "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
315
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
316
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
317
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
318
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
319
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
320
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
321
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
322
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
323
- "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
324
- "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
325
- "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
326
- "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
327
- "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
328
- "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
329
- "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
330
- "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
331
- "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
332
- "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
333
- "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
334
- "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
335
- "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
336
- "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
337
- "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
338
- "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
339
- "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
340
- "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
341
- "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
342
- "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
343
- "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
344
- "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
345
- "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
346
- "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
347
- "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
348
- "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
349
- "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
350
- "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
351
- "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
352
- "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
353
- "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
354
- "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
355
- "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
356
- "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
357
- "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
358
- "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
359
- "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
360
- "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
361
- "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
362
- "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
363
- "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
364
- "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
365
- "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
366
- "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
367
- "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
368
- "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
369
- "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
370
- "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
371
- "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
372
- "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
373
- "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
374
- "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
375
- "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
376
- "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
377
- "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
378
- "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
379
- "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
380
- "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
381
- "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
382
- "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
383
- "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
384
- "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
385
- "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
386
- "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
387
- "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
388
- "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
389
- "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
390
- "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
391
- "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
392
- "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
393
- "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
394
- "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
395
- "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
396
- "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
397
- "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
398
- "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
399
- "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
400
- "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
401
- "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
402
- "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
403
- "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
404
- "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
405
- "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
406
- "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
407
- "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
408
- "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
409
- "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
410
- "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
411
- "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
412
- "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
413
- "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
414
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
415
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
416
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
417
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
418
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
419
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
420
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
421
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
422
- "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
423
- "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
424
- "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
425
- "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
426
- "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
427
- "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
428
- "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
429
- "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
430
- "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
431
- "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
432
- "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
433
- "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
434
- "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
435
- "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
436
- "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
437
- "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
438
- "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
439
- "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
440
- "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
441
- "model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
442
- "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
443
- "model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
444
- "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
445
- "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
446
- "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
447
- "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
448
- "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
449
- "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
450
- "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
451
- "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
452
- "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
453
- "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
454
- "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
455
- "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
456
- "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
457
- "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
458
- "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
459
- "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
460
- "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
461
- "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
462
- "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
463
- "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
464
- "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
465
- "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
466
- "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
467
- "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
468
- "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
469
- "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
470
- "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
471
- "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
472
- "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
473
- "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
474
- "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
475
- "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
476
- "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
477
- "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
478
- "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
479
- "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
480
- "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
481
- "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
482
- "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
483
- "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
484
- "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
485
- "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
486
- "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
487
- "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
488
- "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
489
- "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
490
- "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
491
- "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
492
- "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
493
- "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
494
- "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
495
- "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
496
- "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
497
- "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
498
- "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
499
- "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
500
- "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
501
- "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
502
- "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
503
- "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
504
- "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
505
- "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
506
- "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
507
- "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
508
- "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
509
- "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
510
- "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
511
- "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
512
- "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
513
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
514
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
515
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
516
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
517
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
518
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
519
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
520
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
521
- "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
522
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
523
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
524
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
525
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
526
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
527
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
528
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
529
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
530
- "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
531
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
532
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
533
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
534
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
535
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
536
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
537
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
538
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
539
- "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
540
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
541
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
542
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
543
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
544
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
545
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
546
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
547
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
548
- "model.norm.weight": "model-00007-of-00007.safetensors"
549
- }
550
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<unk>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
tokenizer_config.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": null,
22
- "model_max_length": 2048,
23
- "pad_token": null,
24
- "padding_side": "right",
25
- "sp_model_kwargs": {},
26
- "spaces_between_special_tokens": false,
27
- "tokenizer_class": "LlamaTokenizer",
28
- "unk_token": {
29
- "__type": "AddedToken",
30
- "content": "<unk>",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false
35
- },
36
- "use_default_system_prompt": true
37
- }