CalamitousFelicitousness commited on
Commit
acbaf1c
1 Parent(s): 47284ae

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
4
+ language:
5
+ - en
6
+ pipeline_tag: text-generation
7
+ base_model: Qwen/Qwen2.5-14B
8
+ tags:
9
+ - chat
10
+ ---
11
+
12
+ # Qwen2.5-14B-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 14B 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: 14.7B
28
+ - Number of Paramaters (Non-Embedding): 13.1B
29
+ - Number of Layers: 48
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/Qwen2.5-14B-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
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/Qwen2.5-14B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "activation_scheme": "dynamic",
21
+ "ignored_layers": [
22
+ "lm_head"
23
+ ],
24
+ "quant_method": "fp8"
25
+ },
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 152064
35
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.44.2"
14
+ }
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:d1f985984e86abb8c8fd0355fb4a33b25a85825067f987dc4eef3f22746eae1e
3
+ size 4994302140
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d5a290e8f178c4a38882754efdee8837d26c867428cb2bfc9f175990d4f0dd
3
+ size 4955185672
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc8fec91c4ea76f5a0b1aa8d73c62be617826a0e188b89c706a9715d4c340028
3
+ size 4821486796
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961282a7d1b18000f29487a35cc8e5357190a5222db03c2434bdf25e6d97731f
3
+ size 1557135488
model.safetensors.index.json ADDED
@@ -0,0 +1,922 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16328011072
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
24
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
25
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
34
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
35
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
36
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
37
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
38
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
39
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
40
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
41
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
42
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
43
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
44
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
45
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
46
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
47
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
48
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
49
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
50
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
51
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
52
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
53
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
54
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
55
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
56
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
57
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
58
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
59
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
60
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
61
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
62
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
63
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
64
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
65
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
66
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
67
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
68
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
69
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
70
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
71
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
72
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
73
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
74
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
75
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
76
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
77
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
78
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
79
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
80
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
81
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
82
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
83
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
84
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
87
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
88
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
89
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
91
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
93
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
94
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
95
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
96
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
97
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
98
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
99
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
100
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
101
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
102
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
103
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
106
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
108
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
110
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
112
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
114
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
116
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
117
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
119
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
120
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
122
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
125
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
127
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
129
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
131
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
133
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
135
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
136
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
138
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
141
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
142
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
143
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
144
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
145
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
146
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
147
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
148
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
149
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
150
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
151
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
152
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
154
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
155
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
157
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
158
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
160
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
163
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
164
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
165
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
166
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
167
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
169
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
170
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
171
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
172
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
173
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
174
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
175
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
176
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
177
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
178
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
179
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
182
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
184
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
186
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
187
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
188
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
189
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
190
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
191
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
192
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
193
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
194
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
195
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
196
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
197
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
198
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
199
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
200
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
201
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
202
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
203
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
204
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
205
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
206
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
207
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
208
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
209
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
210
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
211
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
212
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
213
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
214
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
215
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
216
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
217
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
218
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
219
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
220
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
221
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
222
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
223
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
224
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
225
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
226
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
227
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
228
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
229
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
230
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
231
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
232
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
233
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
234
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
236
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
237
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
238
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
239
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
240
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
241
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
242
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
243
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
245
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
247
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
249
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
250
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
252
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
253
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
255
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
258
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
260
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
261
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
262
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
263
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
264
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
265
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
266
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
267
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
268
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
269
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
270
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
271
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
272
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
273
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
274
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
275
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
276
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
277
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
278
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
279
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
280
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
281
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
282
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
283
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
284
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
285
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
287
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
288
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
290
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
291
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
293
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
296
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
298
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
300
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
304
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
306
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
309
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
310
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
312
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
314
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
315
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
317
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
319
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
321
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
323
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
325
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
328
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
331
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
334
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
336
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
338
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
340
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
342
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
344
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
345
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
346
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
347
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
348
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
349
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
350
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
351
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
352
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
353
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
354
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
355
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
356
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
357
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
358
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
359
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
360
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
361
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
362
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
363
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
364
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
365
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
366
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
367
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
368
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
369
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
370
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
371
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
372
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
373
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
374
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
375
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
376
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
377
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
378
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
379
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
380
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
381
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
382
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
383
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
384
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
385
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
386
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
387
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
388
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
389
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
390
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
391
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
392
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
393
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
394
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
395
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
397
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
399
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
400
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
401
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
402
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
403
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
404
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
405
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
406
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
407
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
408
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
409
+ "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
410
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
411
+ "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
412
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
413
+ "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
414
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
415
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
416
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
417
+ "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
418
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
419
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
420
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
421
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
422
+ "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
423
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
424
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
425
+ "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
426
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
427
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
428
+ "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors",
429
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
430
+ "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
431
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
432
+ "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors",
433
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
434
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
435
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
436
+ "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
437
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
438
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
439
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
440
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
441
+ "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
442
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
443
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
444
+ "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
445
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
446
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
447
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
448
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
449
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
450
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
451
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
452
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
453
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
454
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
455
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
456
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
457
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
458
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
459
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
460
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
461
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
462
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
463
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
464
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
465
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
466
+ "model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
467
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
468
+ "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors",
469
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
470
+ "model.layers.30.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
471
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
472
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
473
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
474
+ "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
475
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
476
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors",
477
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
478
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
479
+ "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
480
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
481
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
482
+ "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
483
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
484
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
485
+ "model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
486
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
487
+ "model.layers.31.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
488
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
489
+ "model.layers.31.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
490
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
491
+ "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
492
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
493
+ "model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
494
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
495
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
496
+ "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
497
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
498
+ "model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
499
+ "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
500
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
501
+ "model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
502
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
503
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
504
+ "model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
505
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
506
+ "model.layers.32.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
507
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
508
+ "model.layers.32.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
509
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
510
+ "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
511
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
512
+ "model.layers.32.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
513
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
514
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
515
+ "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
516
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
517
+ "model.layers.32.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
518
+ "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
519
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
520
+ "model.layers.32.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
521
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
522
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
523
+ "model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
524
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
525
+ "model.layers.33.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
526
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
527
+ "model.layers.33.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
528
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
529
+ "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
530
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
531
+ "model.layers.33.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
532
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
533
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
534
+ "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
535
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
536
+ "model.layers.33.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
537
+ "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
538
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
539
+ "model.layers.33.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
540
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
541
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
542
+ "model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
543
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
544
+ "model.layers.34.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
545
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
546
+ "model.layers.34.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
547
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
548
+ "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
549
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
550
+ "model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
551
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
552
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
553
+ "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
554
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
555
+ "model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
556
+ "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
557
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
558
+ "model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
559
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
560
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
561
+ "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
562
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
563
+ "model.layers.35.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
564
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
565
+ "model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
566
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
567
+ "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
568
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
569
+ "model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
570
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
571
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
572
+ "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
573
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
574
+ "model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
575
+ "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
576
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
577
+ "model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
578
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
579
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
580
+ "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
581
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
582
+ "model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
583
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
584
+ "model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
585
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
586
+ "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
587
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
588
+ "model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
589
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
590
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
591
+ "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
592
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
593
+ "model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
594
+ "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
595
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
596
+ "model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
597
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
598
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
599
+ "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
600
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
601
+ "model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
602
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
603
+ "model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
604
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
605
+ "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
606
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
607
+ "model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
608
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
609
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
610
+ "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
611
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
612
+ "model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
613
+ "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
614
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
615
+ "model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
616
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
617
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
618
+ "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
619
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
620
+ "model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
621
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
622
+ "model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
623
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
624
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
625
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
626
+ "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
627
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
628
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
629
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
630
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
631
+ "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
632
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
633
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
634
+ "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
635
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
636
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
637
+ "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
638
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
639
+ "model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
640
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
641
+ "model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
642
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
643
+ "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
644
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
645
+ "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
646
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
647
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
648
+ "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
649
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
650
+ "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
651
+ "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
652
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
653
+ "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
654
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
655
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
656
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
657
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
658
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
659
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
660
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
661
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
662
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
663
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
664
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
665
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
666
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
667
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
668
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
669
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
670
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
671
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
672
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
673
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
674
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
675
+ "model.layers.40.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
676
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
677
+ "model.layers.40.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
678
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
679
+ "model.layers.40.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
680
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
681
+ "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
682
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
683
+ "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
684
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
685
+ "model.layers.40.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
686
+ "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
687
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
688
+ "model.layers.40.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
689
+ "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
690
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
691
+ "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
692
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
693
+ "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
694
+ "model.layers.41.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
695
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
696
+ "model.layers.41.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
697
+ "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
698
+ "model.layers.41.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
699
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
700
+ "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
701
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
702
+ "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
703
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
704
+ "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
705
+ "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
706
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
707
+ "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
708
+ "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
709
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
710
+ "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
711
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
712
+ "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
713
+ "model.layers.42.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
714
+ "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
715
+ "model.layers.42.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
716
+ "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
717
+ "model.layers.42.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
718
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
719
+ "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
720
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
721
+ "model.layers.42.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
722
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
723
+ "model.layers.42.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
724
+ "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
725
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
726
+ "model.layers.42.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
727
+ "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
728
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
729
+ "model.layers.42.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
730
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
731
+ "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
732
+ "model.layers.43.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
733
+ "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
734
+ "model.layers.43.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
735
+ "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
736
+ "model.layers.43.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
737
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
738
+ "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
739
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
740
+ "model.layers.43.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
741
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
742
+ "model.layers.43.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
743
+ "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
744
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
745
+ "model.layers.43.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
746
+ "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
747
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
748
+ "model.layers.43.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
749
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors",
750
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
751
+ "model.layers.44.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
752
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
753
+ "model.layers.44.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
754
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
755
+ "model.layers.44.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
756
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
757
+ "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
758
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
759
+ "model.layers.44.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
760
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
761
+ "model.layers.44.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
762
+ "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
763
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
764
+ "model.layers.44.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
765
+ "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
766
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
767
+ "model.layers.44.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
768
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors",
769
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
770
+ "model.layers.45.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
771
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
772
+ "model.layers.45.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
773
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
774
+ "model.layers.45.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
775
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
776
+ "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
777
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
778
+ "model.layers.45.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
779
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
780
+ "model.layers.45.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
781
+ "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
782
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
783
+ "model.layers.45.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
784
+ "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
785
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
786
+ "model.layers.45.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
787
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors",
788
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
789
+ "model.layers.46.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
790
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
791
+ "model.layers.46.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
792
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
793
+ "model.layers.46.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
794
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
795
+ "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
796
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
797
+ "model.layers.46.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
798
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
799
+ "model.layers.46.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
800
+ "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
801
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
802
+ "model.layers.46.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
803
+ "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
804
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
805
+ "model.layers.46.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
806
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors",
807
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
808
+ "model.layers.47.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors",
809
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
810
+ "model.layers.47.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors",
811
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
812
+ "model.layers.47.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors",
813
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
814
+ "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
815
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
816
+ "model.layers.47.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
817
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
818
+ "model.layers.47.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors",
819
+ "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
820
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
821
+ "model.layers.47.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
822
+ "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
823
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
824
+ "model.layers.47.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
825
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
826
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
827
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
828
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
829
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
830
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
831
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
832
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
833
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
834
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
835
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
836
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
837
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
838
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
839
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
840
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
841
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
842
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
843
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
844
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
845
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
846
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
847
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
848
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
849
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
850
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
851
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
852
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
853
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
854
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
855
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
856
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
857
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
858
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
859
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
860
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
861
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
862
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
863
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
864
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
865
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
866
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
867
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
868
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
869
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
870
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
871
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
872
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
873
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
874
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
875
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
876
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
877
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
878
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
879
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
880
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
881
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
882
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
883
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
884
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
885
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
886
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
887
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
888
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
889
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
890
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
891
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
892
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
893
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
894
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
895
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
896
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
897
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
898
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
899
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
900
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
901
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
902
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
903
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors",
904
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
905
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors",
906
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
907
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors",
908
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
909
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
910
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
911
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
912
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
913
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors",
914
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
915
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
916
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
917
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
918
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
919
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
920
+ "model.norm.weight": "model-00003-of-00004.safetensors"
921
+ }
922
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff