mrfakename littlebird13 commited on
Commit
9edd2c6
·
verified ·
0 Parent(s):

Duplicate from Qwen/Qwen3-Embedding-8B

Browse files

Co-authored-by: cheng <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model:
4
+ - Qwen/Qwen3-8B-Base
5
+ library_name: transformers
6
+ ---
7
+ # Qwen3-Embedding-8B
8
+
9
+ <p align="center">
10
+ <img src="https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen3.png" width="400"/>
11
+ <p>
12
+
13
+ ## Highlights
14
+
15
+ The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
16
+
17
+ **Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios.
18
+
19
+ **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.
20
+
21
+ **Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities.
22
+
23
+ **Qwen3-Embedding-8B** has the following features:
24
+
25
+ - Model Type: Text Embedding
26
+ - Supported Languages: 100+ Languages
27
+ - Number of Paramaters: 8B
28
+ - Context Length: 32k
29
+ - Embedding Dimension: Up to 4096, supports user-defined output dimensions ranging from 32 to 4096
30
+
31
+ For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3-Embedding/), [GitHub](https://github.com/QwenLM/Qwen3-Embedding).
32
+
33
+ ## Qwen3 Embedding Series Model list
34
+
35
+ | Model Type | Models | Size | Layers | Sequence Length | Embedding Dimension | MRL Support | Instruction Aware |
36
+ |------------------|----------------------|------|--------|-----------------|---------------------|-------------|----------------|
37
+ | Text Embedding | [Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) | 0.6B | 28 | 32K | 1024 | Yes | Yes |
38
+ | Text Embedding | [Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) | 4B | 36 | 32K | 2560 | Yes | Yes |
39
+ | Text Embedding | [Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes |
40
+ | Text Reranking | [Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B) | 0.6B | 28 | 32K | - | - | Yes |
41
+ | Text Reranking | [Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) | 4B | 36 | 32K | - | - | Yes |
42
+ | Text Reranking | [Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) | 8B | 36 | 32K | - | - | Yes |
43
+
44
+ > **Note**:
45
+ > - `MRL Support` indicates whether the embedding model supports custom dimensions for the final embedding.
46
+ > - `Instruction Aware` notes whether the embedding or reranking model supports customizing the input instruction according to different tasks.
47
+ > - Our evaluation indicates that, for most downstream tasks, using instructions (instruct) typically yields an improvement of 1% to 5% compared to not using them. Therefore, we recommend that developers create tailored instructions specific to their tasks and scenarios. In multilingual contexts, we also advise users to write their instructions in English, as most instructions utilized during the model training process were originally written in English.
48
+
49
+ ## Usage
50
+
51
+ With Transformers versions earlier than 4.51.0, you may encounter the following error:
52
+ ```
53
+ KeyError: 'qwen3'
54
+ ```
55
+
56
+ ### Transformers Usage
57
+
58
+ ```python
59
+ # Requires transformers>=4.51.0
60
+
61
+ import torch
62
+ import torch.nn.functional as F
63
+
64
+ from torch import Tensor
65
+ from transformers import AutoTokenizer, AutoModel
66
+
67
+
68
+ def last_token_pool(last_hidden_states: Tensor,
69
+ attention_mask: Tensor) -> Tensor:
70
+ left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
71
+ if left_padding:
72
+ return last_hidden_states[:, -1]
73
+ else:
74
+ sequence_lengths = attention_mask.sum(dim=1) - 1
75
+ batch_size = last_hidden_states.shape[0]
76
+ return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
77
+
78
+
79
+ def get_detailed_instruct(task_description: str, query: str) -> str:
80
+ return f'Instruct: {task_description}\nQuery:{query}'
81
+
82
+ def tokenize(tokenizer, input_texts, eod_id, max_length):
83
+ batch_dict = tokenizer(input_texts, padding=False, truncation=True, max_length=max_length-2)
84
+ for seq, att in zip(batch_dict["input_ids"], batch_dict["attention_mask"]):
85
+ seq.append(eod_id)
86
+ att.append(1)
87
+ batch_dict = tokenizer.pad(batch_dict, padding=True, return_tensors="pt")
88
+ return batch_dict
89
+
90
+ # Each query must come with a one-sentence instruction that describes the task
91
+ task = 'Given a web search query, retrieve relevant passages that answer the query'
92
+
93
+ queries = [
94
+ get_detailed_instruct(task, 'What is the capital of China?'),
95
+ get_detailed_instruct(task, 'Explain gravity')
96
+ ]
97
+ # No need to add instruction for retrieval documents
98
+ documents = [
99
+ "The capital of China is Beijing.",
100
+ "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
101
+ ]
102
+ input_texts = queries + documents
103
+
104
+ tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-Embedding-8B', padding_side='left')
105
+ model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-8B')
106
+
107
+ # We recommend enabling flash_attention_2 for better acceleration and memory saving.
108
+ # model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-8B', attn_implementation="flash_attention_2", torch_dtype=torch.float16).cuda()
109
+
110
+ eod_id = tokenizer.convert_tokens_to_ids("<|endoftext|>")
111
+ max_length = 8192
112
+
113
+ # Tokenize the input texts
114
+ batch_dict = tokenize(tokenizer, input_texts, eod_id, max_length)
115
+ batch_dict.to(model.device)
116
+ outputs = model(**batch_dict)
117
+ embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
118
+
119
+ # normalize embeddings
120
+ embeddings = F.normalize(embeddings, p=2, dim=1)
121
+ scores = (embeddings[:2] @ embeddings[2:].T)
122
+ print(scores.tolist())
123
+ ```
124
+ 📌 **Tip**: We recommend that developers customize the `instruct` according to their specific scenarios, tasks, and languages. Our tests have shown that in most retrieval scenarios, not using an `instruct` on the query side can lead to a drop in retrieval performance by approximately 1% to 5%.
125
+
126
+ ## Evaluation
127
+
128
+ ### MTEB (Multilingual)
129
+
130
+ | Model | Size | Mean (Task) | Mean (Type) | Bitxt Mining | Class. | Clust. | Inst. Retri. | Multi. Class. | Pair. Class. | Rerank | Retri. | STS |
131
+ |----------------------------------|:-------:|:-------------:|:-------------:|:--------------:|:--------:|:--------:|:--------------:|:---------------:|:--------------:|:--------:|:--------:|:------:|
132
+ | NV-Embed-v2 | 7B | 56.29 | 49.58 | 57.84 | 57.29 | 40.80 | 1.04 | 18.63 | 78.94 | 63.82 | 56.72 | 71.10|
133
+ | GritLM-7B | 7B | 60.92 | 53.74 | 70.53 | 61.83 | 49.75 | 3.45 | 22.77 | 79.94 | 63.78 | 58.31 | 73.33|
134
+ | BGE-M3 | 0.6B | 59.56 | 52.18 | 79.11 | 60.35 | 40.88 | -3.11 | 20.1 | 80.76 | 62.79 | 54.60 | 74.12|
135
+ | multilingual-e5-large-instruct | 0.6B | 63.22 | 55.08 | 80.13 | 64.94 | 50.75 | -0.40 | 22.91 | 80.86 | 62.61 | 57.12 | 76.81|
136
+ | gte-Qwen2-1.5B-instruct | 1.5B | 59.45 | 52.69 | 62.51 | 58.32 | 52.05 | 0.74 | 24.02 | 81.58 | 62.58 | 60.78 | 71.61|
137
+ | gte-Qwen2-7b-Instruct | 7B | 62.51 | 55.93 | 73.92 | 61.55 | 52.77 | 4.94 | 25.48 | 85.13 | 65.55 | 60.08 | 73.98|
138
+ | text-embedding-3-large | - | 58.93 | 51.41 | 62.17 | 60.27 | 46.89 | -2.68 | 22.03 | 79.17 | 63.89 | 59.27 | 71.68|
139
+ | Cohere-embed-multilingual-v3.0 | - | 61.12 | 53.23 | 70.50 | 62.95 | 46.89 | -1.89 | 22.74 | 79.88 | 64.07 | 59.16 | 74.80|
140
+ | gemini-embedding-exp-03-07 | - | 68.37 | 59.59 | 79.28 | 71.82 | 54.59 | 5.18 | **29.16** | 83.63 | 65.58 | 67.71 | 79.40|
141
+ | **Qwen3-Embedding-0.6B** | 0.6B | 64.33 | 56.00 | 72.22 | 66.83 | 52.33 | 5.09 | 24.59 | 80.83 | 61.41 | 64.64 | 76.17|
142
+ | **Qwen3-Embedding-4B** | 4B | 69.45 | 60.86 | 79.36 | 72.33 | 57.15 | **11.56** | 26.77 | 85.05 | 65.08 | 69.60 | 80.86|
143
+ | **Qwen3-Embedding-8B** | 8B | **70.58** | **61.69** | **80.89** | **74.00** | **57.65** | 10.06 | 28.66 | **86.40** | **65.63** | **70.88** | **81.08** |
144
+
145
+ > **Note**: For compared models, the scores are retrieved from MTEB online [leaderboard](https://huggingface.co/spaces/mteb/leaderboard) on May 24th, 2025.
146
+
147
+ ### MTEB (Eng v2)
148
+
149
+ | MTEB English / Models | Param. | Mean(Task) | Mean(Type) | Class. | Clust. | Pair Class. | Rerank. | Retri. | STS | Summ. |
150
+ |--------------------------------|:--------:|:------------:|:------------:|:--------:|:--------:|:-------------:|:---------:|:--------:|:-------:|:-------:|
151
+ | multilingual-e5-large-instruct | 0.6B | 65.53 | 61.21 | 75.54 | 49.89 | 86.24 | 48.74 | 53.47 | 84.72 | 29.89 |
152
+ | NV-Embed-v2 | 7.8B | 69.81 | 65.00 | 87.19 | 47.66 | 88.69 | 49.61 | 62.84 | 83.82 | 35.21 |
153
+ | GritLM-7B | 7.2B | 67.07 | 63.22 | 81.25 | 50.82 | 87.29 | 49.59 | 54.95 | 83.03 | 35.65 |
154
+ | gte-Qwen2-1.5B-instruct | 1.5B | 67.20 | 63.26 | 85.84 | 53.54 | 87.52 | 49.25 | 50.25 | 82.51 | 33.94 |
155
+ | stella_en_1.5B_v5 | 1.5B | 69.43 | 65.32 | 89.38 | 57.06 | 88.02 | 50.19 | 52.42 | 83.27 | 36.91 |
156
+ | gte-Qwen2-7B-instruct | 7.6B | 70.72 | 65.77 | 88.52 | 58.97 | 85.9 | 50.47 | 58.09 | 82.69 | 35.74 |
157
+ | gemini-embedding-exp-03-07 | - | 73.3 | 67.67 | 90.05 | **59.39** | **87.7** | 48.59 | 64.35 | 85.29 | **38.28** |
158
+ | **Qwen3-Embedding-0.6B** | 0.6B | 70.70 | 64.88 | 85.76 | 54.05 | 84.37 | 48.18 | 61.83 | 86.57 | 33.43 |
159
+ | **Qwen3-Embedding-4B** | 4B | 74.60 | 68.10 | 89.84 | 57.51 | 87.01 | 50.76 | 68.46 | **88.72** | 34.39 |
160
+ | **Qwen3-Embedding-8B** | 8B | **75.22** | **68.71** | **90.43** | 58.57 | 87.52 | **51.56** | **69.44** | 88.58 | 34.83 |
161
+
162
+ ### C-MTEB (MTEB Chinese)
163
+
164
+ | C-MTEB | Param. | Mean(Task) | Mean(Type) | Class. | Clust. | Pair Class. | Rerank. | Retr. | STS |
165
+ |------------------|--------|------------|------------|--------|--------|-------------|---------|-------|-------|
166
+ | multilingual-e5-large-instruct | 0.6B | 58.08 | 58.24 | 69.80 | 48.23 | 64.52 | 57.45 | 63.65 | 45.81 |
167
+ | bge-multilingual-gemma2 | 9B | 67.64 |68.52 | 75.31 | 59.30 | 86.67 | 68.28 | 73.73 | 55.19 |
168
+ | gte-Qwen2-1.5B-instruct | 1.5B | 67.12 | 67.79 | 72.53 | 54.61 | 79.5 | 68.21 | 71.86 | 60.05 |
169
+ | gte-Qwen2-7B-instruct | 7.6B | 71.62 | 72.19 | 75.77 | 66.06 | 81.16 | 69.24 | 75.70 | 65.20 |
170
+ | ritrieve_zh_v1 | 0.3B | 72.71 | 73.85 | 76.88 | 66.5 | **85.98** | **72.86** | 76.97 | **63.92** |
171
+ | **Qwen3-Embedding-0.6B** | 0.6B | 66.33 | 67.45 | 71.40 | 68.74 | 76.42 | 62.58 | 71.03 | 54.52 |
172
+ | **Qwen3-Embedding-4B** | 4B | 72.27 | 73.51 | 75.46 | 77.89 | 83.34 | 66.05 | 77.03 | 61.26 |
173
+ | **Qwen3-Embedding-8B** | 8B | **73.84** | **75.00** | **76.97** | **80.08** | 84.23 | 66.99 | **78.21** | 63.53 |
174
+
175
+
176
+ ## Citation
177
+
178
+ If you find our work helpful, feel free to give us a cite.
179
+
180
+ ```
181
+ @misc{qwen3-embedding,
182
+ title = {Qwen3-Embedding},
183
+ url = {https://qwenlm.github.io/blog/qwen3/},
184
+ author = {Qwen Team},
185
+ month = {May},
186
+ year = {2025}
187
+ }
188
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 36,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.2",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151665
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.51.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b343597fe840706146144699a8b9188dd3387e43eb61faf0231b70b249d451
3
+ size 4900037024
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff635b0f6dbbaad2a2d633ef037ec0a39bc165cc1806c712fbd6fcbcb4526c0
3
+ size 4915959512
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b1d4c53d84eb018f642cad7b373f0aabf79699872d8702c1f38577c0a59a2f
3
+ size 4983067656
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cbc9c60375693629f25743c1e77ebb1724af58e671b2376463193c7fd21ef6
3
+ size 335570376
model.safetensors.index.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15134590976
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
13
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
16
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
24
+ "layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
25
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
26
+ "layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
27
+ "layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
28
+ "layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
29
+ "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
31
+ "layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
32
+ "layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
33
+ "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
35
+ "layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
36
+ "layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
37
+ "layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
38
+ "layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
39
+ "layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
40
+ "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
42
+ "layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
43
+ "layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
44
+ "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
46
+ "layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
47
+ "layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
48
+ "layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
49
+ "layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
50
+ "layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
51
+ "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
57
+ "layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
60
+ "layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
68
+ "layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
71
+ "layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72
+ "layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73
+ "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75
+ "layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
76
+ "layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
79
+ "layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
80
+ "layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
81
+ "layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
82
+ "layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
83
+ "layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
84
+ "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86
+ "layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
87
+ "layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
88
+ "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
90
+ "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
91
+ "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
92
+ "layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
93
+ "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94
+ "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
95
+ "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
96
+ "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
97
+ "layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
98
+ "layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
99
+ "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
101
+ "layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
102
+ "layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
103
+ "layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
104
+ "layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
107
+ "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108
+ "layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109
+ "layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
112
+ "layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
115
+ "layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
123
+ "layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
126
+ "layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
129
+ "layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
130
+ "layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
134
+ "layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
137
+ "layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
139
+ "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
140
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
141
+ "layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
142
+ "layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
143
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
144
+ "layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
145
+ "layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
146
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
147
+ "layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
148
+ "layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
149
+ "layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
150
+ "layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
151
+ "layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
152
+ "layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
153
+ "layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
154
+ "layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
155
+ "layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
156
+ "layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
157
+ "layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
158
+ "layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
159
+ "layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
160
+ "layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
161
+ "layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
162
+ "layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
163
+ "layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
164
+ "layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
165
+ "layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
166
+ "layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
167
+ "layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
168
+ "layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
169
+ "layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
170
+ "layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
171
+ "layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
172
+ "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
174
+ "layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
175
+ "layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
176
+ "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
178
+ "layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
179
+ "layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
180
+ "layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
181
+ "layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
182
+ "layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
183
+ "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
185
+ "layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
186
+ "layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
187
+ "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
189
+ "layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
190
+ "layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
191
+ "layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
192
+ "layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
193
+ "layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
194
+ "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
196
+ "layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
197
+ "layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
198
+ "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
200
+ "layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
201
+ "layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
202
+ "layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
203
+ "layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
211
+ "layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
214
+ "layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218
+ "layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
219
+ "layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
220
+ "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
222
+ "layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
223
+ "layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
224
+ "layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
225
+ "layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226
+ "layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
227
+ "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
229
+ "layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
230
+ "layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
231
+ "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
232
+ "layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
233
+ "layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
234
+ "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
235
+ "layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
236
+ "layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
237
+ "layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
238
+ "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
239
+ "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
240
+ "layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
241
+ "layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
242
+ "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
243
+ "layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
244
+ "layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
245
+ "layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
246
+ "layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
247
+ "layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248
+ "layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
255
+ "layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
258
+ "layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
266
+ "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
269
+ "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
271
+ "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
272
+ "layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
273
+ "layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
274
+ "layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
275
+ "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
276
+ "layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
277
+ "layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
278
+ "layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
279
+ "layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
280
+ "layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
281
+ "layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
282
+ "layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
283
+ "layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
284
+ "layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
285
+ "layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
286
+ "layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
287
+ "layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
288
+ "layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
289
+ "layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
290
+ "layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
291
+ "layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
292
+ "layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
293
+ "layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
294
+ "layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
295
+ "layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
296
+ "layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
297
+ "layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
298
+ "layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
299
+ "layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
300
+ "layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
301
+ "layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
302
+ "layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
303
+ "layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
304
+ "layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
305
+ "layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
306
+ "layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
307
+ "layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
308
+ "layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
309
+ "layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
310
+ "layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
311
+ "layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
312
+ "layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
313
+ "layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
314
+ "layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
315
+ "layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
316
+ "layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
317
+ "layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
318
+ "layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
319
+ "layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
320
+ "layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
321
+ "layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
322
+ "layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
323
+ "layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
324
+ "layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
325
+ "layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
326
+ "layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
327
+ "layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
328
+ "layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
329
+ "layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
330
+ "layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
331
+ "layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
332
+ "layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
333
+ "layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
334
+ "layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
335
+ "layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
336
+ "layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
337
+ "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
338
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
339
+ "layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
340
+ "layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
341
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
342
+ "layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
343
+ "layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
344
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
345
+ "layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
346
+ "layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
347
+ "layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
348
+ "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
349
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
350
+ "layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
351
+ "layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
352
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
353
+ "layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
354
+ "layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
355
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
356
+ "layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
357
+ "layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
358
+ "layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
359
+ "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
360
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
361
+ "layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
362
+ "layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
363
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
364
+ "layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
365
+ "layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
366
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
367
+ "layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
368
+ "layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
369
+ "layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
370
+ "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
371
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
372
+ "layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
373
+ "layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
374
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
375
+ "layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
376
+ "layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
377
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
378
+ "layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
379
+ "layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
380
+ "layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
381
+ "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
382
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
383
+ "layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
384
+ "layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
385
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386
+ "layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
387
+ "layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
388
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
389
+ "layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
390
+ "layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391
+ "layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
392
+ "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
393
+ "layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
394
+ "layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
395
+ "layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
396
+ "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
397
+ "layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
398
+ "layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
399
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
400
+ "layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
401
+ "layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
402
+ "layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
403
+ "norm.weight": "model-00004-of-00004.safetensors"
404
+ }
405
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are 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 a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff