Shitao commited on
Commit
7b03a43
·
verified ·
1 Parent(s): 5b58b37

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1536,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": true,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - zh
4
+ - en
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - transformers
10
+ pipeline_tag: sentence-similarity
11
+ library_name: sentence-transformers
12
+ license: apache-2.0
13
+ ---
14
+
15
+ <h1 align="center">FlagEmbedding</h1>
16
+
17
+ For more details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
18
+
19
+ **BGE-Code-v1** is an LLM-based code embedding model that supports code retrieval, text retrieval, and multilingual retrieval. It primarily demonstrates the following capabilities:
20
+ - Superior Code Retrieval Performance: The model demonstrates exceptional code retrieval capabilities, supporting natural language queries in both English and Chinese, as well as 20 programming languages.
21
+ - Robust Text Retrieval Capabilities: The model maintains strong text retrieval capabilities comparable to text embedding models of similar scale.
22
+ - Extensive Multilingual Support: BGE-Code-v1 offers comprehensive multilingual retrieval capabilities, excelling in languages such as English, Chinese, Japanese, French, and more.
23
+
24
+ ## Usage
25
+
26
+ ### Using FlagEmbedding
27
+
28
+ ```
29
+ git clone https://github.com/FlagOpen/FlagEmbedding.git
30
+ cd FlagEmbedding
31
+ pip install -e .
32
+ ```
33
+
34
+ ```python
35
+ from FlagEmbedding import FlagLLMModel
36
+ queries = [
37
+ "Delete the record with ID 4 from the 'Staff' table.",
38
+ 'Delete all records in the "Livestock" table where age is greater than 5'
39
+ ]
40
+ documents = [
41
+ "DELETE FROM Staff WHERE StaffID = 4;",
42
+ "DELETE FROM Livestock WHERE age > 5;"
43
+ ]
44
+ model = FlagLLMModel('BAAI/BGE-Code-v1',
45
+ query_instruction_format="<instruct>{}\n<query>{}",
46
+ query_instruction_for_retrieval="Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
47
+ trust_remote_code=True,
48
+ use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
49
+ embeddings_1 = model.encode_queries(queries)
50
+ embeddings_2 = model.encode_corpus(documents)
51
+ similarity = embeddings_1 @ embeddings_2.T
52
+ print(similarity)
53
+ ```
54
+
55
+ By default, FlagLLMModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs. You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable.
56
+
57
+ ### Using Sentence Transformers
58
+
59
+ ```python
60
+ from sentence_transformers import SentenceTransformer
61
+ import torch
62
+
63
+ # Load the model, optionally in float16 precision for faster inference
64
+ model = SentenceTransformer("BAAI/bge-code-v1", model_kwargs={"torch_dtype": torch.float16, "trust_remote_code": True}, tokenizer_kwargs={"trust_remote_code": True})
65
+
66
+ # Prepare a prompt given an instruction
67
+ instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
68
+ prompt = f'<instruct>{instruction}\n<query>'
69
+ # Prepare queries and documents
70
+ queries = [
71
+ "Delete the record with ID 4 from the 'Staff' table.",
72
+ 'Delete all records in the "Livestock" table where age is greater than 5'
73
+ ]
74
+ documents = [
75
+ "DELETE FROM Staff WHERE StaffID = 4;",
76
+ "DELETE FROM Livestock WHERE age > 5;"
77
+ ]
78
+
79
+ # Compute the query and document embeddings
80
+ query_embeddings = model.encode(queries, prompt=prompt)
81
+ document_embeddings = model.encode(documents)
82
+
83
+ # Compute the cosine similarity between the query and document embeddings
84
+ similarities = model.similarity(query_embeddings, document_embeddings)
85
+ print(similarities)
86
+ ```
87
+
88
+ ### Using HuggingFace Transformers
89
+
90
+ ```python
91
+ import torch
92
+ import torch.nn.functional as F
93
+
94
+ from torch import Tensor
95
+ from transformers import AutoTokenizer, AutoModel
96
+
97
+
98
+ def last_token_pool(last_hidden_states: Tensor,
99
+ attention_mask: Tensor) -> Tensor:
100
+ left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
101
+ if left_padding:
102
+ return last_hidden_states[:, -1]
103
+ else:
104
+ sequence_lengths = attention_mask.sum(dim=1) - 1
105
+ batch_size = last_hidden_states.shape[0]
106
+ return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
107
+
108
+
109
+ def get_detailed_instruct(task_description: str, query: str) -> str:
110
+ return f'<instruct>{task_description}\n<query>{query}'
111
+
112
+
113
+ instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
114
+ queries = [
115
+ "Delete the record with ID 4 from the 'Staff' table.",
116
+ 'Delete all records in the "Livestock" table where age is greater than 5'
117
+ ]
118
+ documents = [
119
+ "DELETE FROM Staff WHERE StaffID = 4;",
120
+ "DELETE FROM Livestock WHERE age > 5;"
121
+ ]
122
+ input_texts = queries + documents
123
+
124
+ tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-code-v1', trust_remote_code=True)
125
+ model = AutoModel.from_pretrained('BAAI/bge-code-v1', trust_remote_code=True)
126
+ model.eval()
127
+
128
+ max_length = 4096
129
+ # Tokenize the input texts
130
+ batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt', pad_to_multiple_of=8)
131
+
132
+ with torch.no_grad():
133
+ outputs = model(**batch_dict)
134
+ embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
135
+
136
+ # normalize embeddings
137
+ embeddings = F.normalize(embeddings, p=2, dim=1)
138
+ scores = (embeddings[:2] @ embeddings[2:].T) * 100
139
+ print(scores.tolist())
140
+ ```
141
+
142
+ ## Evaluation
143
+
144
+ **BGE-Code-v1** achieves state-of-the-art performance on both the CoIR and CodeRAG benchmarks.
145
+
146
+ - CoIR
147
+
148
+ | | CodeXEmbed-2B | CodeXEmbed-7B | Voyage-Code-002 | Voyage-Code-003 | BGE-Code-v1 |
149
+ |---------------------------------------|---------------|---------------|-----------------|-----------------|-----------|
150
+ | Apps | 76.86 | 85.38 | 26.52 | 93.62 | 98.08 |
151
+ | CosQA | 40.47 | 42.47 | 29.79 | 34.45 | 46.72 |
152
+ | Text2SQL | 78.42 | 78.94 | 69.26 | 62.87 | 64.35 |
153
+ | CSN | 87.87 | 89.67 | 81.79 | 89.35 | 89.53 |
154
+ | CSN-CCR | 97.66 | 97.95 | 73.45 | 90.05 | 98.30 |
155
+ | CodeTrans-Contest | 90.30 | 94.45 | 72.77 | 94.96 | 94.38 |
156
+ | CodeTrans-DL | 38.57 | 40.46 | 27.48 | 38.57 | 46.13 |
157
+ | StackOverFlow-QA | 94.47 | 96.33 | 67.68 | 97.17 | 95.35 |
158
+ | CodeFeedBack-ST | 86.36 | 87.53 | 65.35 | 90.67 | 90.56 |
159
+ | CodeFeedBack-MT | 65.51 | 68.83 | 28.74 | 93.58 | 94.38 |
160
+ | AVG | 75.65 | 78.20 | 56.26 | 78.53 | 81.77 |
161
+
162
+ - CodedRAG
163
+
164
+ | | HummanEval | MBPP | DS-1000 | ODEX | RepoEval | SWE-bench-Lite | AVG |
165
+ | --------------- | ---------- | ---- | ------- | ---- | -------- | -------------- | ---- |
166
+ | SFR | 100.0 | 99.0 | 19.3 | 37.1 | 83.8 | 62.7 | 67.0 |
167
+ | Jina-v2-code | 100.0 | 97.7 | 26.2 | 19.9 | 90.5 | 58.3 | 65.4 |
168
+ | CodeXEmbed-2B | 100.0 | 97.4 | 25.4 | 23.9 | 88.7 | 52.4 | 64.6 |
169
+ | Voyage-Code-002 | 100.0 | 99.0 | 33.1 | 26.6 | 94.3 | 29.1 | 63.7 |
170
+ | Voyage-Code-003 | 100.0 | 99.6 | 38.9 | 36.3 | 90.0 | 70.1 | 72.5 |
171
+ | BGE-Code-v1 | 100.0 | 99.2 | 40.9 | 36.1 | 93.1 | 67.4 | 72.8 |
172
+
173
+ ## Citation
174
+
175
+ If you find this repository useful, please consider giving a star :star: and citation
176
+
177
+ ```
178
+ @article{bge-llm,
179
+ title={Making text embedders few-shot learners},
180
+ author={Li, Chaofan and Qin, MingHao and Xiao, Shitao and Chen, Jianlyu and Luo, Kun and Shao, Yingxia and Lian, Defu and Liu, Zheng},
181
+ journal={arXiv preprint arXiv:2409.15700},
182
+ year={2024}
183
+ }
184
+
185
+ @misc{bge-m3,
186
+ title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
187
+ author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
188
+ year={2024},
189
+ eprint={2402.03216},
190
+ archivePrefix={arXiv},
191
+ primaryClass={cs.CL}
192
+ }
193
+
194
+
195
+ @misc{bge_embedding,
196
+ title={C-Pack: Packaged Resources To Advance General Chinese Embedding},
197
+ author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
198
+ year={2023},
199
+ eprint={2309.07597},
200
+ archivePrefix={arXiv},
201
+ primaryClass={cs.CL}
202
+ }
203
+ ```
added_tokens.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<instruct>": 151665,
4
+ "<query>": 151666,
5
+ "<tool_call>": 151657,
6
+ "<|box_end|>": 151649,
7
+ "<|box_start|>": 151648,
8
+ "<|endoftext|>": 151643,
9
+ "<|file_sep|>": 151664,
10
+ "<|fim_middle|>": 151660,
11
+ "<|fim_pad|>": 151662,
12
+ "<|fim_prefix|>": 151659,
13
+ "<|fim_suffix|>": 151661,
14
+ "<|im_end|>": 151645,
15
+ "<|im_start|>": 151644,
16
+ "<|image_pad|>": 151655,
17
+ "<|object_ref_end|>": 151647,
18
+ "<|object_ref_start|>": 151646,
19
+ "<|quad_end|>": 151651,
20
+ "<|quad_start|>": 151650,
21
+ "<|repo_name|>": 151663,
22
+ "<|video_pad|>": 151656,
23
+ "<|vision_end|>": 151653,
24
+ "<|vision_pad|>": 151654,
25
+ "<|vision_start|>": 151652
26
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bge-code-v1",
3
+ "architectures": [
4
+ "Qwen2Model"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.49.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151667
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.49.0",
5
+ "pytorch": "2.5.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0012a815833b137559c60485e3d087fb029e034b7b5e5c18fa9cabcc3faafc
3
+ size 4995016160
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d0d51780cad746744bed246b4c13e520e458ba36509c33aff1ed0c9ac16d71
3
+ size 1178224504
model.safetensors.index.json ADDED
@@ -0,0 +1,345 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6173204480
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
13
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
16
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
18
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
25
+ "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
28
+ "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
+ "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
37
+ "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
40
+ "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
42
+ "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
58
+ "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
61
+ "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
62
+ "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
73
+ "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
85
+ "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
109
+ "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
112
+ "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
+ "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
114
+ "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
121
+ "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
+ "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
+ "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
+ "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
133
+ "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
136
+ "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
137
+ "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
138
+ "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
157
+ "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
166
+ "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
169
+ "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
170
+ "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
171
+ "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
172
+ "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
173
+ "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
174
+ "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
175
+ "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
177
+ "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
178
+ "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
181
+ "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
182
+ "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
183
+ "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
184
+ "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
185
+ "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
186
+ "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
187
+ "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
193
+ "layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
196
+ "layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
+ "layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
198
+ "layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
199
+ "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
201
+ "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
202
+ "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
203
+ "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
205
+ "layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
206
+ "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
207
+ "layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
208
+ "layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
209
+ "layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
210
+ "layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
211
+ "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
+ "layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
214
+ "layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
215
+ "layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
216
+ "layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
217
+ "layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
218
+ "layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
219
+ "layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
220
+ "layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
221
+ "layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
222
+ "layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
223
+ "layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
224
+ "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
225
+ "layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
226
+ "layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
227
+ "layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
228
+ "layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
229
+ "layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
232
+ "layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
234
+ "layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
235
+ "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
237
+ "layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
238
+ "layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
+ "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
241
+ "layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
242
+ "layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
243
+ "layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
244
+ "layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
245
+ "layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
246
+ "layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
247
+ "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
249
+ "layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
250
+ "layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
251
+ "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
253
+ "layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
254
+ "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
255
+ "layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
256
+ "layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
257
+ "layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
258
+ "layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
259
+ "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
260
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
261
+ "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
262
+ "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
263
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
264
+ "layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
265
+ "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
268
+ "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
269
+ "layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
270
+ "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
272
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
273
+ "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
274
+ "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
275
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
276
+ "layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
277
+ "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
278
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
279
+ "layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
280
+ "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
281
+ "layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
282
+ "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
+ "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
292
+ "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
294
+ "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
296
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
297
+ "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
298
+ "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
299
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
300
+ "layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
301
+ "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
302
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
303
+ "layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
304
+ "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
305
+ "layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
306
+ "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
307
+ "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
308
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
309
+ "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
+ "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
311
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
313
+ "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
315
+ "layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
316
+ "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
+ "layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
+ "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
320
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
321
+ "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
322
+ "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
323
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
324
+ "layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
325
+ "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
326
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
327
+ "layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
328
+ "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
329
+ "layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
330
+ "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
331
+ "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
332
+ "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
333
+ "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
334
+ "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
335
+ "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
336
+ "layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
337
+ "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
338
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
339
+ "layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
340
+ "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
341
+ "layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
342
+ "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
343
+ "norm.weight": "model-00002-of-00002.safetensors"
344
+ }
345
+ }
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 256,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<instruct>",
4
+ "<query>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56524092f5d0676e63537511b535e73e7580a7efe440247ef3fa43d019a0af0
3
+ size 11422261
tokenizer_config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<instruct>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "151666": {
191
+ "content": "<query>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ }
198
+ },
199
+ "additional_special_tokens": [
200
+ "<instruct>",
201
+ "<query>"
202
+ ],
203
+ "auto_map": {
204
+ "AutoTokenizer": [
205
+ "/share_2/chaofan/models/CodeR-full--tokenization_qwen.Qwen2Tokenizer",
206
+ null
207
+ ]
208
+ },
209
+ "bos_token": null,
210
+ "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",
211
+ "clean_up_tokenization_spaces": false,
212
+ "eos_token": "<|endoftext|>",
213
+ "errors": "replace",
214
+ "extra_special_tokens": {},
215
+ "model_max_length": 256,
216
+ "pad_token": "<|endoftext|>",
217
+ "split_special_tokens": false,
218
+ "tokenizer_class": "Qwen2Tokenizer",
219
+ "unk_token": null
220
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff