DrNicefellow commited on
Commit
0527b0e
1 Parent(s): d945e98

Upload 13 files

Browse files
README.md CHANGED
@@ -1,21 +1,131 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
3
  ---
4
 
5
- This is a 8.0bpw quantized version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) made with [exllamav2](https://github.com/turboderp/exllamav2).
6
 
 
7
 
8
- ## License
9
 
10
- This model is available under the Apache 2.0 License.
 
 
 
11
 
 
 
 
 
 
 
 
 
 
 
12
 
13
- ## Discord Server
14
 
15
- Join our Discord server [here](https://discord.gg/xhcBDEM3).
16
 
 
17
 
18
- ## Feeling Generous? 😊
 
 
 
19
 
20
- Eager to buy me a cup of 2$ coffe or iced tea?🍵☕ Sure, here is the link: [https://ko-fi.com/drnicefellow](https://ko-fi.com/drnicefellow). Please add a note on which one you want me to drink?
21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ license_link: https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE
4
+ language:
5
+ - en
6
+ pipeline_tag: text-generation
7
+ base_model: Qwen/Qwen2.5-32B
8
+ tags:
9
+ - chat
10
  ---
11
 
12
+ # Qwen2.5-32B-Instruct
13
 
14
+ ## Introduction
15
 
16
+ Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
17
 
18
+ - Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
19
+ - Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
20
+ - **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
21
+ - **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
22
 
23
+ **This repo contains the instruction-tuned 32B Qwen2.5 model**, which has the following features:
24
+ - Type: Causal Language Models
25
+ - Training Stage: Pretraining & Post-training
26
+ - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
27
+ - Number of Parameters: 32.5B
28
+ - Number of Paramaters (Non-Embedding): 31.0B
29
+ - Number of Layers: 64
30
+ - Number of Attention Heads (GQA): 40 for Q and 8 for KV
31
+ - Context Length: Full 131,072 tokens and generation 8192 tokens
32
+ - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts.
33
 
34
+ For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
35
 
36
+ ## Requirements
37
 
38
+ The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
39
 
40
+ With `transformers<4.37.0`, you will encounter the following error:
41
+ ```
42
+ KeyError: 'qwen2'
43
+ ```
44
 
45
+ ## Quickstart
46
 
47
+ Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
48
+
49
+ ```python
50
+ from transformers import AutoModelForCausalLM, AutoTokenizer
51
+
52
+ model_name = "Qwen/Qwen2.5-32B-Instruct"
53
+
54
+ model = AutoModelForCausalLM.from_pretrained(
55
+ model_name,
56
+ torch_dtype="auto",
57
+ device_map="auto"
58
+ )
59
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
60
+
61
+ prompt = "Give me a short introduction to large language model."
62
+ messages = [
63
+ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
64
+ {"role": "user", "content": prompt}
65
+ ]
66
+ text = tokenizer.apply_chat_template(
67
+ messages,
68
+ tokenize=False,
69
+ add_generation_prompt=True
70
+ )
71
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
72
+
73
+ generated_ids = model.generate(
74
+ **model_inputs,
75
+ max_new_tokens=512
76
+ )
77
+ generated_ids = [
78
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
79
+ ]
80
+
81
+ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
82
+ ```
83
+
84
+ ### Processing Long Texts
85
+
86
+ The current `config.json` is set for context length up to 32,768 tokens.
87
+ To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
88
+
89
+ For supported frameworks, you could add the following to `config.json` to enable YaRN:
90
+ ```json
91
+ {
92
+ ...,
93
+ "rope_scaling": {
94
+ "factor": 4.0,
95
+ "original_max_position_embeddings": 32768,
96
+ "type": "yarn"
97
+ }
98
+ }
99
+ ```
100
+
101
+ For deployment, we recommend using vLLM.
102
+ Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM.
103
+ Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**.
104
+ We advise adding the `rope_scaling` configuration only when processing long contexts is required.
105
+
106
+ ## Evaluation & Performance
107
+
108
+ Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/).
109
+
110
+ For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
111
+
112
+ ## Citation
113
+
114
+ If you find our work helpful, feel free to give us a cite.
115
+
116
+ ```
117
+ @misc{qwen2.5,
118
+ title = {Qwen2.5: A Party of Foundation Models},
119
+ url = {https://qwenlm.github.io/blog/qwen2.5/},
120
+ author = {Qwen Team},
121
+ month = {September},
122
+ year = {2024}
123
+ }
124
+
125
+ @article{qwen2,
126
+ title={Qwen2 Technical Report},
127
+ author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
128
+ journal={arXiv preprint arXiv:2407.10671},
129
+ year={2024}
130
+ }
131
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 27648,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 70,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 152064,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.2.2",
30
+ "bits": 8.0,
31
+ "head_bits": 8,
32
+ "calibration": {
33
+ "rows": 115,
34
+ "length": 2048,
35
+ "dataset": "(default)"
36
+ }
37
+ }
38
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "pad_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_p": 0.8,
12
+ "top_k": 20,
13
+ "transformers_version": "4.37.0"
14
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/Qwen/Qwen2.5-32B-Instruct
2
+ branch: main
3
+ download date: 2024-09-18 22:58:43
4
+ sha256sum:
5
+ fa006a0382517a4e9a8781d8e7d3405cd6bdd1b9100fb344d73f925b7da9341c model-00001-of-00017.safetensors
6
+ 0d7f28a4ba7135c2c8365016170cfa25723f65ec41e32ec9a3c81746e4395615 model-00002-of-00017.safetensors
7
+ 8f4b7b811a7ecf117c179ac9413b7a746f2fc0707a41ae4b2efd0282e73bed85 model-00003-of-00017.safetensors
8
+ de8ab9cb81e6798031d2cf9ef6d15a0034b77fceeba3d4e011647943c8b99afb model-00004-of-00017.safetensors
9
+ fa86494f0074cc36c610aa54e7bde03edefc57a9be7636216277bd5ed8b8bfda model-00005-of-00017.safetensors
10
+ c8fa152bd8a23bab2c0cfca43ff9f586bccd82b1cb67f2f84231f31d0f3cab47 model-00006-of-00017.safetensors
11
+ 5e33e16319d18d1e180187d9f858deddbbaf06d950abc88941bf027d1439c7bc model-00007-of-00017.safetensors
12
+ 8561b86737884397772bb990b38c0efe896f66ed27815ca207ddc8ec7965ffe4 model-00008-of-00017.safetensors
13
+ 47f562bf77d986b53c5390b01a30a77576c3eed69191b484cf88b53bb64bce19 model-00009-of-00017.safetensors
14
+ 359450e2c9e261751b5803fcdd1d0a040029a6119a271dd8592d7bb37fa722b5 model-00010-of-00017.safetensors
15
+ 836f0570f5694ce1d55f505064190e2688926dad4f033384ae519d96faaad670 model-00011-of-00017.safetensors
16
+ 5307431e385a177375a5aa887eb1c546f3413dd2e2269c291672f11f752842b4 model-00012-of-00017.safetensors
17
+ 9b2657db02572dd4370186b35c0e0fa70218d7e2ec1190e4dc4a755c5cbd430e model-00013-of-00017.safetensors
18
+ b5f1f8af3b6bbf734790985590752fb815dd69566cf05ee578d70af74ace1d4c model-00014-of-00017.safetensors
19
+ 8cdfcbf8913e10056c981db2db817f92c8601998deb9eabcae14fade98d76c14 model-00015-of-00017.safetensors
20
+ 977b3d2ca7f97dc3b518ed5087ddc43ccf7afb371190828f2334d7e4c81224ee model-00016-of-00017.safetensors
21
+ 2853695483f9c61a8bd8b109025b3c591214a0362992fa844537f09acc81bd03 model-00017-of-00017.safetensors
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 65527752704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00017-of-00017.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00017.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00017.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00017.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00017.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00017.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00017.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00017.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00017.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00017.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00017.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00017.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00017.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00017.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00017.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00017.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00006-of-00017.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00017.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00017.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00017.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00017.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00006-of-00017.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00017.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00017.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00017.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00017.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00017.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00007-of-00017.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00007-of-00017.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00007-of-00017.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00007-of-00017.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00017.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00017.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00017.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00008-of-00017.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00008-of-00017.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00008-of-00017.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00008-of-00017.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00017.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00017.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00017.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00009-of-00017.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00009-of-00017.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00009-of-00017.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00009-of-00017.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00017.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00017.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00017.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00010-of-00017.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00010-of-00017.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00010-of-00017.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00010-of-00017.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00017.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00010-of-00017.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00010-of-00017.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00011-of-00017.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00011-of-00017.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00011-of-00017.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00011-of-00017.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00017.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00017.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00017.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00012-of-00017.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00012-of-00017.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00012-of-00017.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00012-of-00017.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00012-of-00017.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00012-of-00017.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00012-of-00017.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00013-of-00017.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00013-of-00017.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00013-of-00017.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00013-of-00017.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00013-of-00017.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00013-of-00017.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00013-of-00017.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00014-of-00017.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00014-of-00017.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00014-of-00017.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00014-of-00017.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00014-of-00017.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00014-of-00017.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00014-of-00017.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00015-of-00017.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00015-of-00017.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00015-of-00017.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00015-of-00017.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00017.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00015-of-00017.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00015-of-00017.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00016-of-00017.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00017.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00017.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00017.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00017.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00016-of-00017.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00016-of-00017.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00016-of-00017.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00016-of-00017.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00016-of-00017.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00016-of-00017.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00017-of-00017.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00017-of-00017.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00017-of-00017.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00017-of-00017.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00017.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00017.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00017.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00017.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
776
+ "model.norm.weight": "model-00017-of-00017.safetensors"
777
+ }
778
+ }
output-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae990569719f968cd282a2edf17f1b31ad2ba848918e2dd143a4ad9bbcbfe480
3
+ size 8529852952
output-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354ab7abcf10d422c0a403b300eb93c9a3cc717db13006a7d6a65b264392ce6a
3
+ size 8585662884
output-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee0674c575476cdbf0a5e4c4290ea9dda79f6d9786ae52dc2a5987bb8fdd5ff
3
+ size 8525057702
output-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35df80f36ad4142b2113736098e850eb56b16a127967beaca791d3184dbf4633
3
+ size 4607334928
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ }
180
+ },
181
+ "additional_special_tokens": [
182
+ "<|im_start|>",
183
+ "<|im_end|>",
184
+ "<|object_ref_start|>",
185
+ "<|object_ref_end|>",
186
+ "<|box_start|>",
187
+ "<|box_end|>",
188
+ "<|quad_start|>",
189
+ "<|quad_end|>",
190
+ "<|vision_start|>",
191
+ "<|vision_end|>",
192
+ "<|vision_pad|>",
193
+ "<|image_pad|>",
194
+ "<|video_pad|>"
195
+ ],
196
+ "bos_token": null,
197
+ "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",
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "model_max_length": 131072,
202
+ "pad_token": "<|endoftext|>",
203
+ "split_special_tokens": false,
204
+ "tokenizer_class": "Qwen2Tokenizer",
205
+ "unk_token": null,
206
+ "add_bos_token": false
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff