Hugging Face's logo

typealias
/
internlm2_5-7b-chat-4bit

Text Generation
Transformers
PyTorch
Safetensors
internlm2
feature-extraction
conversational
custom_code
4-bit precision
awq
Model card Files Community
typealias commited on
Commit
40429ad
•
1 Parent(s): a874318

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. README.md +68 -0
  2. config.json +41 -0
  3. generation_config.json +7 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +554 -0
  8. pytorch_model.bin.index.json +554 -0
  9. special_tokens_map.json +38 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +98 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ pipeline_tag: text-generation
4
+ ---
5
+ <div align="center">
6
+ <img src="https://raw.githubusercontent.com/InternLM/lmdeploy/0be9e7ab6fe9a066cfb0a09d0e0c8d2e28435e58/resources/lmdeploy-logo.svg" width="450"/>
7
+ </div>
8
+
9
+ # INT4 Weight-only Quantization and Deployment (W4A16)
10
+
11
+ LMDeploy adopts [AWQ](https://arxiv.org/abs/2306.00978) algorithm for 4bit weight-only quantization. By developed the high-performance cuda kernel, the 4bit quantized model inference achieves up to 2.4x faster than FP16.
12
+
13
+ LMDeploy supports the following NVIDIA GPU for W4A16 inference:
14
+
15
+ - Turing(sm75): 20 series, T4
16
+
17
+ - Ampere(sm80,sm86): 30 series, A10, A16, A30, A100
18
+
19
+ - Ada Lovelace(sm90): 40 series
20
+
21
+ Before proceeding with the quantization and inference, please ensure that lmdeploy is installed.
22
+
23
+ ```shell
24
+ pip install lmdeploy[all]
25
+ ```
26
+
27
+ This article comprises the following sections:
28
+
29
+ <!-- toc -->
30
+
31
+ - [Inference](#inference)
32
+ - [Evaluation](#evaluation)
33
+ - [Service](#service)
34
+
35
+ <!-- tocstop -->
36
+ ## Inference
37
+
38
+ Trying the following codes, you can perform the batched offline inference with the quantized model:
39
+
40
+ ```python
41
+ from lmdeploy import pipeline, TurbomindEngineConfig
42
+ engine_config = TurbomindEngineConfig(model_format='awq')
43
+ pipe = pipeline("internlm/internlm2_5-7b-chat-4bit", backend_config=engine_config)
44
+ response = pipe(["Hi, pls intro yourself", "Shanghai is"])
45
+ print(response)
46
+ ```
47
+
48
+ For more information about the pipeline parameters, please refer to [here](https://github.com/InternLM/lmdeploy/blob/main/docs/en/inference/pipeline.md).
49
+
50
+ ## Evaluation
51
+
52
+ Please overview [this guide](https://opencompass.readthedocs.io/en/latest/advanced_guides/evaluation_turbomind.html) about model evaluation with LMDeploy.
53
+
54
+ ## Service
55
+
56
+ LMDeploy's `api_server` enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup:
57
+
58
+ ```shell
59
+ lmdeploy serve api_server internlm/internlm2_5-7b-chat-4bit --backend turbomind --model-format awq
60
+ ```
61
+
62
+ The default port of `api_server` is `23333`. After the server is launched, you can communicate with server on terminal through `api_client`:
63
+
64
+ ```shell
65
+ lmdeploy serve api_client http://0.0.0.0:23333
66
+ ```
67
+
68
+ You can overview and try out `api_server` APIs online by swagger UI at `http://0.0.0.0:23333`, or you can also read the API specification from [here](https://github.com/InternLM/lmdeploy/blob/main/docs/en/serving/restful_api.md).
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nvme/shared_data/InternLM/internlm2_5-7b-chat",
3
+ "architectures": [
4
+ "InternLM2ForCausalLM"
5
+ ],
6
+ "attn_implementation": "eager",
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
9
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
10
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
11
+ },
12
+ "bias": false,
13
+ "bos_token_id": 1,
14
+ "eos_token_id": 2,
15
+ "fp16": true,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 4096,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 14336,
20
+ "max_position_embeddings": 32768,
21
+ "model_type": "internlm2",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 8,
25
+ "pad_token_id": 2,
26
+ "quantization_config": {
27
+ "bits": 4,
28
+ "group_size": 128,
29
+ "quant_method": "awq",
30
+ "version": "gemm",
31
+ "zero_point": true
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 1000000,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.40.1",
39
+ "use_cache": false,
40
+ "vocab_size": 92544
41
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.40.1"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a15cf6767b864b7a395b9874682275ae524a3eb998bf98d1efeaba4a5084d1
3
+ size 1384550088
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123bc6a3ff4c4822104b6529eda73af9e3dec0067e1d45c1742af1c8c25320df
3
+ size 1019380312
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0ad632fc20940e6fb47c123769fc3ba86b60461c95f53c4adbfceffd4390d3
3
+ size 980417432
model.safetensors.index.json ADDED
@@ -0,0 +1,554 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5142749184
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0.attention.wo.qweight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.attention.wo.qzeros": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.attention.wo.scales": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.attention.wqkv.scales": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.attention_norm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.attention.wo.qweight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.attention.wo.qzeros": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.attention.wo.scales": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.attention.wqkv.scales": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.attention_norm.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.attention.wo.qweight": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.attention.wo.qzeros": "model-00001-of-00003.safetensors",
42
+ "model.layers.10.attention.wo.scales": "model-00001-of-00003.safetensors",
43
+ "model.layers.10.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.attention.wqkv.scales": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.attention_norm.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.10.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
48
+ "model.layers.10.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
50
+ "model.layers.10.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
51
+ "model.layers.10.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
52
+ "model.layers.10.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
53
+ "model.layers.10.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
54
+ "model.layers.10.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
55
+ "model.layers.10.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
56
+ "model.layers.10.ffn_norm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.11.attention.wo.qweight": "model-00002-of-00003.safetensors",
58
+ "model.layers.11.attention.wo.qzeros": "model-00002-of-00003.safetensors",
59
+ "model.layers.11.attention.wo.scales": "model-00002-of-00003.safetensors",
60
+ "model.layers.11.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
61
+ "model.layers.11.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
62
+ "model.layers.11.attention.wqkv.scales": "model-00002-of-00003.safetensors",
63
+ "model.layers.11.attention_norm.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.11.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
65
+ "model.layers.11.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
66
+ "model.layers.11.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
67
+ "model.layers.11.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
68
+ "model.layers.11.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
69
+ "model.layers.11.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
70
+ "model.layers.11.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
71
+ "model.layers.11.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
72
+ "model.layers.11.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
73
+ "model.layers.11.ffn_norm.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.12.attention.wo.qweight": "model-00002-of-00003.safetensors",
75
+ "model.layers.12.attention.wo.qzeros": "model-00002-of-00003.safetensors",
76
+ "model.layers.12.attention.wo.scales": "model-00002-of-00003.safetensors",
77
+ "model.layers.12.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
78
+ "model.layers.12.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
79
+ "model.layers.12.attention.wqkv.scales": "model-00002-of-00003.safetensors",
80
+ "model.layers.12.attention_norm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.12.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
82
+ "model.layers.12.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
83
+ "model.layers.12.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
84
+ "model.layers.12.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
87
+ "model.layers.12.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
88
+ "model.layers.12.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
89
+ "model.layers.12.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
90
+ "model.layers.12.ffn_norm.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.13.attention.wo.qweight": "model-00002-of-00003.safetensors",
92
+ "model.layers.13.attention.wo.qzeros": "model-00002-of-00003.safetensors",
93
+ "model.layers.13.attention.wo.scales": "model-00002-of-00003.safetensors",
94
+ "model.layers.13.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
95
+ "model.layers.13.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
96
+ "model.layers.13.attention.wqkv.scales": "model-00002-of-00003.safetensors",
97
+ "model.layers.13.attention_norm.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.13.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
99
+ "model.layers.13.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
100
+ "model.layers.13.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
101
+ "model.layers.13.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
102
+ "model.layers.13.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
103
+ "model.layers.13.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
104
+ "model.layers.13.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
105
+ "model.layers.13.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
106
+ "model.layers.13.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
107
+ "model.layers.13.ffn_norm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.14.attention.wo.qweight": "model-00002-of-00003.safetensors",
109
+ "model.layers.14.attention.wo.qzeros": "model-00002-of-00003.safetensors",
110
+ "model.layers.14.attention.wo.scales": "model-00002-of-00003.safetensors",
111
+ "model.layers.14.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
112
+ "model.layers.14.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
113
+ "model.layers.14.attention.wqkv.scales": "model-00002-of-00003.safetensors",
114
+ "model.layers.14.attention_norm.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.14.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
116
+ "model.layers.14.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
117
+ "model.layers.14.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
118
+ "model.layers.14.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
119
+ "model.layers.14.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
120
+ "model.layers.14.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
121
+ "model.layers.14.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
122
+ "model.layers.14.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
123
+ "model.layers.14.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
124
+ "model.layers.14.ffn_norm.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.15.attention.wo.qweight": "model-00002-of-00003.safetensors",
126
+ "model.layers.15.attention.wo.qzeros": "model-00002-of-00003.safetensors",
127
+ "model.layers.15.attention.wo.scales": "model-00002-of-00003.safetensors",
128
+ "model.layers.15.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
129
+ "model.layers.15.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
130
+ "model.layers.15.attention.wqkv.scales": "model-00002-of-00003.safetensors",
131
+ "model.layers.15.attention_norm.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.15.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
133
+ "model.layers.15.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
134
+ "model.layers.15.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
135
+ "model.layers.15.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
136
+ "model.layers.15.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
137
+ "model.layers.15.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
138
+ "model.layers.15.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
139
+ "model.layers.15.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
140
+ "model.layers.15.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
141
+ "model.layers.15.ffn_norm.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.16.attention.wo.qweight": "model-00002-of-00003.safetensors",
143
+ "model.layers.16.attention.wo.qzeros": "model-00002-of-00003.safetensors",
144
+ "model.layers.16.attention.wo.scales": "model-00002-of-00003.safetensors",
145
+ "model.layers.16.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
146
+ "model.layers.16.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
147
+ "model.layers.16.attention.wqkv.scales": "model-00002-of-00003.safetensors",
148
+ "model.layers.16.attention_norm.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.16.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
150
+ "model.layers.16.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
151
+ "model.layers.16.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
152
+ "model.layers.16.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
153
+ "model.layers.16.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
154
+ "model.layers.16.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
155
+ "model.layers.16.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
156
+ "model.layers.16.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
157
+ "model.layers.16.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
158
+ "model.layers.16.ffn_norm.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.17.attention.wo.qweight": "model-00002-of-00003.safetensors",
160
+ "model.layers.17.attention.wo.qzeros": "model-00002-of-00003.safetensors",
161
+ "model.layers.17.attention.wo.scales": "model-00002-of-00003.safetensors",
162
+ "model.layers.17.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
163
+ "model.layers.17.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
164
+ "model.layers.17.attention.wqkv.scales": "model-00002-of-00003.safetensors",
165
+ "model.layers.17.attention_norm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.17.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
167
+ "model.layers.17.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
168
+ "model.layers.17.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
169
+ "model.layers.17.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
170
+ "model.layers.17.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
171
+ "model.layers.17.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
172
+ "model.layers.17.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
173
+ "model.layers.17.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
174
+ "model.layers.17.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
175
+ "model.layers.17.ffn_norm.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.18.attention.wo.qweight": "model-00002-of-00003.safetensors",
177
+ "model.layers.18.attention.wo.qzeros": "model-00002-of-00003.safetensors",
178
+ "model.layers.18.attention.wo.scales": "model-00002-of-00003.safetensors",
179
+ "model.layers.18.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
180
+ "model.layers.18.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
181
+ "model.layers.18.attention.wqkv.scales": "model-00002-of-00003.safetensors",
182
+ "model.layers.18.attention_norm.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.18.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
184
+ "model.layers.18.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
185
+ "model.layers.18.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
186
+ "model.layers.18.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
187
+ "model.layers.18.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
188
+ "model.layers.18.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
189
+ "model.layers.18.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
190
+ "model.layers.18.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
191
+ "model.layers.18.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
192
+ "model.layers.18.ffn_norm.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.19.attention.wo.qweight": "model-00002-of-00003.safetensors",
194
+ "model.layers.19.attention.wo.qzeros": "model-00002-of-00003.safetensors",
195
+ "model.layers.19.attention.wo.scales": "model-00002-of-00003.safetensors",
196
+ "model.layers.19.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
197
+ "model.layers.19.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
198
+ "model.layers.19.attention.wqkv.scales": "model-00002-of-00003.safetensors",
199
+ "model.layers.19.attention_norm.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.19.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
201
+ "model.layers.19.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
202
+ "model.layers.19.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
203
+ "model.layers.19.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
204
+ "model.layers.19.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
205
+ "model.layers.19.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
206
+ "model.layers.19.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
207
+ "model.layers.19.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
208
+ "model.layers.19.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
209
+ "model.layers.19.ffn_norm.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.2.attention.wo.qweight": "model-00001-of-00003.safetensors",
211
+ "model.layers.2.attention.wo.qzeros": "model-00001-of-00003.safetensors",
212
+ "model.layers.2.attention.wo.scales": "model-00001-of-00003.safetensors",
213
+ "model.layers.2.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
214
+ "model.layers.2.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
215
+ "model.layers.2.attention.wqkv.scales": "model-00001-of-00003.safetensors",
216
+ "model.layers.2.attention_norm.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.2.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
218
+ "model.layers.2.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
219
+ "model.layers.2.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
220
+ "model.layers.2.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
221
+ "model.layers.2.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
222
+ "model.layers.2.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
223
+ "model.layers.2.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
224
+ "model.layers.2.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
225
+ "model.layers.2.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
226
+ "model.layers.2.ffn_norm.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.20.attention.wo.qweight": "model-00002-of-00003.safetensors",
228
+ "model.layers.20.attention.wo.qzeros": "model-00002-of-00003.safetensors",
229
+ "model.layers.20.attention.wo.scales": "model-00002-of-00003.safetensors",
230
+ "model.layers.20.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
231
+ "model.layers.20.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
232
+ "model.layers.20.attention.wqkv.scales": "model-00002-of-00003.safetensors",
233
+ "model.layers.20.attention_norm.weight": "model-00002-of-00003.safetensors",
234
+ "model.layers.20.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
235
+ "model.layers.20.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
236
+ "model.layers.20.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
237
+ "model.layers.20.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
238
+ "model.layers.20.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
239
+ "model.layers.20.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
240
+ "model.layers.20.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
241
+ "model.layers.20.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
242
+ "model.layers.20.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
243
+ "model.layers.20.ffn_norm.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.21.attention.wo.qweight": "model-00002-of-00003.safetensors",
245
+ "model.layers.21.attention.wo.qzeros": "model-00002-of-00003.safetensors",
246
+ "model.layers.21.attention.wo.scales": "model-00002-of-00003.safetensors",
247
+ "model.layers.21.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
248
+ "model.layers.21.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
249
+ "model.layers.21.attention.wqkv.scales": "model-00002-of-00003.safetensors",
250
+ "model.layers.21.attention_norm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.21.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
252
+ "model.layers.21.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
253
+ "model.layers.21.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
254
+ "model.layers.21.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
255
+ "model.layers.21.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
256
+ "model.layers.21.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
257
+ "model.layers.21.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
258
+ "model.layers.21.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
259
+ "model.layers.21.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
260
+ "model.layers.21.ffn_norm.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.22.attention.wo.qweight": "model-00002-of-00003.safetensors",
262
+ "model.layers.22.attention.wo.qzeros": "model-00002-of-00003.safetensors",
263
+ "model.layers.22.attention.wo.scales": "model-00002-of-00003.safetensors",
264
+ "model.layers.22.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
265
+ "model.layers.22.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
266
+ "model.layers.22.attention.wqkv.scales": "model-00002-of-00003.safetensors",
267
+ "model.layers.22.attention_norm.weight": "model-00002-of-00003.safetensors",
268
+ "model.layers.22.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
269
+ "model.layers.22.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
270
+ "model.layers.22.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
271
+ "model.layers.22.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
272
+ "model.layers.22.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
273
+ "model.layers.22.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
274
+ "model.layers.22.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
275
+ "model.layers.22.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
276
+ "model.layers.22.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
277
+ "model.layers.22.ffn_norm.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.23.attention.wo.qweight": "model-00002-of-00003.safetensors",
279
+ "model.layers.23.attention.wo.qzeros": "model-00002-of-00003.safetensors",
280
+ "model.layers.23.attention.wo.scales": "model-00002-of-00003.safetensors",
281
+ "model.layers.23.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
282
+ "model.layers.23.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
283
+ "model.layers.23.attention.wqkv.scales": "model-00002-of-00003.safetensors",
284
+ "model.layers.23.attention_norm.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.23.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
286
+ "model.layers.23.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
287
+ "model.layers.23.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
288
+ "model.layers.23.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
289
+ "model.layers.23.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
290
+ "model.layers.23.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
291
+ "model.layers.23.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
292
+ "model.layers.23.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
293
+ "model.layers.23.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
294
+ "model.layers.23.ffn_norm.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.24.attention.wo.qweight": "model-00002-of-00003.safetensors",
296
+ "model.layers.24.attention.wo.qzeros": "model-00002-of-00003.safetensors",
297
+ "model.layers.24.attention.wo.scales": "model-00002-of-00003.safetensors",
298
+ "model.layers.24.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
299
+ "model.layers.24.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
300
+ "model.layers.24.attention.wqkv.scales": "model-00002-of-00003.safetensors",
301
+ "model.layers.24.attention_norm.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.24.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
303
+ "model.layers.24.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
304
+ "model.layers.24.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
305
+ "model.layers.24.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
306
+ "model.layers.24.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
307
+ "model.layers.24.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
308
+ "model.layers.24.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
309
+ "model.layers.24.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
310
+ "model.layers.24.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
311
+ "model.layers.24.ffn_norm.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.25.attention.wo.qweight": "model-00002-of-00003.safetensors",
313
+ "model.layers.25.attention.wo.qzeros": "model-00002-of-00003.safetensors",
314
+ "model.layers.25.attention.wo.scales": "model-00002-of-00003.safetensors",
315
+ "model.layers.25.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
316
+ "model.layers.25.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
317
+ "model.layers.25.attention.wqkv.scales": "model-00002-of-00003.safetensors",
318
+ "model.layers.25.attention_norm.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.25.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
320
+ "model.layers.25.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
321
+ "model.layers.25.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
322
+ "model.layers.25.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
323
+ "model.layers.25.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
324
+ "model.layers.25.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
325
+ "model.layers.25.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
326
+ "model.layers.25.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
327
+ "model.layers.25.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
328
+ "model.layers.25.ffn_norm.weight": "model-00002-of-00003.safetensors",
329
+ "model.layers.26.attention.wo.qweight": "model-00002-of-00003.safetensors",
330
+ "model.layers.26.attention.wo.qzeros": "model-00002-of-00003.safetensors",
331
+ "model.layers.26.attention.wo.scales": "model-00002-of-00003.safetensors",
332
+ "model.layers.26.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
333
+ "model.layers.26.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
334
+ "model.layers.26.attention.wqkv.scales": "model-00002-of-00003.safetensors",
335
+ "model.layers.26.attention_norm.weight": "model-00002-of-00003.safetensors",
336
+ "model.layers.26.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
337
+ "model.layers.26.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
338
+ "model.layers.26.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
339
+ "model.layers.26.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
340
+ "model.layers.26.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
341
+ "model.layers.26.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
342
+ "model.layers.26.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
343
+ "model.layers.26.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
344
+ "model.layers.26.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
345
+ "model.layers.26.ffn_norm.weight": "model-00002-of-00003.safetensors",
346
+ "model.layers.27.attention.wo.qweight": "model-00002-of-00003.safetensors",
347
+ "model.layers.27.attention.wo.qzeros": "model-00002-of-00003.safetensors",
348
+ "model.layers.27.attention.wo.scales": "model-00002-of-00003.safetensors",
349
+ "model.layers.27.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
350
+ "model.layers.27.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
351
+ "model.layers.27.attention.wqkv.scales": "model-00002-of-00003.safetensors",
352
+ "model.layers.27.attention_norm.weight": "model-00002-of-00003.safetensors",
353
+ "model.layers.27.feed_forward.w1.qweight": "model-00002-of-00003.safetensors",
354
+ "model.layers.27.feed_forward.w1.qzeros": "model-00002-of-00003.safetensors",
355
+ "model.layers.27.feed_forward.w1.scales": "model-00002-of-00003.safetensors",
356
+ "model.layers.27.feed_forward.w2.qweight": "model-00002-of-00003.safetensors",
357
+ "model.layers.27.feed_forward.w2.qzeros": "model-00002-of-00003.safetensors",
358
+ "model.layers.27.feed_forward.w2.scales": "model-00002-of-00003.safetensors",
359
+ "model.layers.27.feed_forward.w3.qweight": "model-00002-of-00003.safetensors",
360
+ "model.layers.27.feed_forward.w3.qzeros": "model-00002-of-00003.safetensors",
361
+ "model.layers.27.feed_forward.w3.scales": "model-00002-of-00003.safetensors",
362
+ "model.layers.27.ffn_norm.weight": "model-00002-of-00003.safetensors",
363
+ "model.layers.28.attention.wo.qweight": "model-00002-of-00003.safetensors",
364
+ "model.layers.28.attention.wo.qzeros": "model-00002-of-00003.safetensors",
365
+ "model.layers.28.attention.wo.scales": "model-00002-of-00003.safetensors",
366
+ "model.layers.28.attention.wqkv.qweight": "model-00002-of-00003.safetensors",
367
+ "model.layers.28.attention.wqkv.qzeros": "model-00002-of-00003.safetensors",
368
+ "model.layers.28.attention.wqkv.scales": "model-00002-of-00003.safetensors",
369
+ "model.layers.28.attention_norm.weight": "model-00003-of-00003.safetensors",
370
+ "model.layers.28.feed_forward.w1.qweight": "model-00003-of-00003.safetensors",
371
+ "model.layers.28.feed_forward.w1.qzeros": "model-00003-of-00003.safetensors",
372
+ "model.layers.28.feed_forward.w1.scales": "model-00003-of-00003.safetensors",
373
+ "model.layers.28.feed_forward.w2.qweight": "model-00003-of-00003.safetensors",
374
+ "model.layers.28.feed_forward.w2.qzeros": "model-00003-of-00003.safetensors",
375
+ "model.layers.28.feed_forward.w2.scales": "model-00003-of-00003.safetensors",
376
+ "model.layers.28.feed_forward.w3.qweight": "model-00003-of-00003.safetensors",
377
+ "model.layers.28.feed_forward.w3.qzeros": "model-00003-of-00003.safetensors",
378
+ "model.layers.28.feed_forward.w3.scales": "model-00003-of-00003.safetensors",
379
+ "model.layers.28.ffn_norm.weight": "model-00003-of-00003.safetensors",
380
+ "model.layers.29.attention.wo.qweight": "model-00003-of-00003.safetensors",
381
+ "model.layers.29.attention.wo.qzeros": "model-00003-of-00003.safetensors",
382
+ "model.layers.29.attention.wo.scales": "model-00003-of-00003.safetensors",
383
+ "model.layers.29.attention.wqkv.qweight": "model-00003-of-00003.safetensors",
384
+ "model.layers.29.attention.wqkv.qzeros": "model-00003-of-00003.safetensors",
385
+ "model.layers.29.attention.wqkv.scales": "model-00003-of-00003.safetensors",
386
+ "model.layers.29.attention_norm.weight": "model-00003-of-00003.safetensors",
387
+ "model.layers.29.feed_forward.w1.qweight": "model-00003-of-00003.safetensors",
388
+ "model.layers.29.feed_forward.w1.qzeros": "model-00003-of-00003.safetensors",
389
+ "model.layers.29.feed_forward.w1.scales": "model-00003-of-00003.safetensors",
390
+ "model.layers.29.feed_forward.w2.qweight": "model-00003-of-00003.safetensors",
391
+ "model.layers.29.feed_forward.w2.qzeros": "model-00003-of-00003.safetensors",
392
+ "model.layers.29.feed_forward.w2.scales": "model-00003-of-00003.safetensors",
393
+ "model.layers.29.feed_forward.w3.qweight": "model-00003-of-00003.safetensors",
394
+ "model.layers.29.feed_forward.w3.qzeros": "model-00003-of-00003.safetensors",
395
+ "model.layers.29.feed_forward.w3.scales": "model-00003-of-00003.safetensors",
396
+ "model.layers.29.ffn_norm.weight": "model-00003-of-00003.safetensors",
397
+ "model.layers.3.attention.wo.qweight": "model-00001-of-00003.safetensors",
398
+ "model.layers.3.attention.wo.qzeros": "model-00001-of-00003.safetensors",
399
+ "model.layers.3.attention.wo.scales": "model-00001-of-00003.safetensors",
400
+ "model.layers.3.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
401
+ "model.layers.3.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
402
+ "model.layers.3.attention.wqkv.scales": "model-00001-of-00003.safetensors",
403
+ "model.layers.3.attention_norm.weight": "model-00001-of-00003.safetensors",
404
+ "model.layers.3.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
405
+ "model.layers.3.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
406
+ "model.layers.3.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
407
+ "model.layers.3.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
408
+ "model.layers.3.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
409
+ "model.layers.3.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
410
+ "model.layers.3.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
411
+ "model.layers.3.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
412
+ "model.layers.3.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
413
+ "model.layers.3.ffn_norm.weight": "model-00001-of-00003.safetensors",
414
+ "model.layers.30.attention.wo.qweight": "model-00003-of-00003.safetensors",
415
+ "model.layers.30.attention.wo.qzeros": "model-00003-of-00003.safetensors",
416
+ "model.layers.30.attention.wo.scales": "model-00003-of-00003.safetensors",
417
+ "model.layers.30.attention.wqkv.qweight": "model-00003-of-00003.safetensors",
418
+ "model.layers.30.attention.wqkv.qzeros": "model-00003-of-00003.safetensors",
419
+ "model.layers.30.attention.wqkv.scales": "model-00003-of-00003.safetensors",
420
+ "model.layers.30.attention_norm.weight": "model-00003-of-00003.safetensors",
421
+ "model.layers.30.feed_forward.w1.qweight": "model-00003-of-00003.safetensors",
422
+ "model.layers.30.feed_forward.w1.qzeros": "model-00003-of-00003.safetensors",
423
+ "model.layers.30.feed_forward.w1.scales": "model-00003-of-00003.safetensors",
424
+ "model.layers.30.feed_forward.w2.qweight": "model-00003-of-00003.safetensors",
425
+ "model.layers.30.feed_forward.w2.qzeros": "model-00003-of-00003.safetensors",
426
+ "model.layers.30.feed_forward.w2.scales": "model-00003-of-00003.safetensors",
427
+ "model.layers.30.feed_forward.w3.qweight": "model-00003-of-00003.safetensors",
428
+ "model.layers.30.feed_forward.w3.qzeros": "model-00003-of-00003.safetensors",
429
+ "model.layers.30.feed_forward.w3.scales": "model-00003-of-00003.safetensors",
430
+ "model.layers.30.ffn_norm.weight": "model-00003-of-00003.safetensors",
431
+ "model.layers.31.attention.wo.qweight": "model-00003-of-00003.safetensors",
432
+ "model.layers.31.attention.wo.qzeros": "model-00003-of-00003.safetensors",
433
+ "model.layers.31.attention.wo.scales": "model-00003-of-00003.safetensors",
434
+ "model.layers.31.attention.wqkv.qweight": "model-00003-of-00003.safetensors",
435
+ "model.layers.31.attention.wqkv.qzeros": "model-00003-of-00003.safetensors",
436
+ "model.layers.31.attention.wqkv.scales": "model-00003-of-00003.safetensors",
437
+ "model.layers.31.attention_norm.weight": "model-00003-of-00003.safetensors",
438
+ "model.layers.31.feed_forward.w1.qweight": "model-00003-of-00003.safetensors",
439
+ "model.layers.31.feed_forward.w1.qzeros": "model-00003-of-00003.safetensors",
440
+ "model.layers.31.feed_forward.w1.scales": "model-00003-of-00003.safetensors",
441
+ "model.layers.31.feed_forward.w2.qweight": "model-00003-of-00003.safetensors",
442
+ "model.layers.31.feed_forward.w2.qzeros": "model-00003-of-00003.safetensors",
443
+ "model.layers.31.feed_forward.w2.scales": "model-00003-of-00003.safetensors",
444
+ "model.layers.31.feed_forward.w3.qweight": "model-00003-of-00003.safetensors",
445
+ "model.layers.31.feed_forward.w3.qzeros": "model-00003-of-00003.safetensors",
446
+ "model.layers.31.feed_forward.w3.scales": "model-00003-of-00003.safetensors",
447
+ "model.layers.31.ffn_norm.weight": "model-00003-of-00003.safetensors",
448
+ "model.layers.4.attention.wo.qweight": "model-00001-of-00003.safetensors",
449
+ "model.layers.4.attention.wo.qzeros": "model-00001-of-00003.safetensors",
450
+ "model.layers.4.attention.wo.scales": "model-00001-of-00003.safetensors",
451
+ "model.layers.4.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
452
+ "model.layers.4.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
453
+ "model.layers.4.attention.wqkv.scales": "model-00001-of-00003.safetensors",
454
+ "model.layers.4.attention_norm.weight": "model-00001-of-00003.safetensors",
455
+ "model.layers.4.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
456
+ "model.layers.4.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
457
+ "model.layers.4.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
458
+ "model.layers.4.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
459
+ "model.layers.4.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
460
+ "model.layers.4.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
461
+ "model.layers.4.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
462
+ "model.layers.4.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
463
+ "model.layers.4.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
464
+ "model.layers.4.ffn_norm.weight": "model-00001-of-00003.safetensors",
465
+ "model.layers.5.attention.wo.qweight": "model-00001-of-00003.safetensors",
466
+ "model.layers.5.attention.wo.qzeros": "model-00001-of-00003.safetensors",
467
+ "model.layers.5.attention.wo.scales": "model-00001-of-00003.safetensors",
468
+ "model.layers.5.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
469
+ "model.layers.5.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
470
+ "model.layers.5.attention.wqkv.scales": "model-00001-of-00003.safetensors",
471
+ "model.layers.5.attention_norm.weight": "model-00001-of-00003.safetensors",
472
+ "model.layers.5.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
473
+ "model.layers.5.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
474
+ "model.layers.5.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
475
+ "model.layers.5.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
476
+ "model.layers.5.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
477
+ "model.layers.5.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
478
+ "model.layers.5.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
479
+ "model.layers.5.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
480
+ "model.layers.5.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
481
+ "model.layers.5.ffn_norm.weight": "model-00001-of-00003.safetensors",
482
+ "model.layers.6.attention.wo.qweight": "model-00001-of-00003.safetensors",
483
+ "model.layers.6.attention.wo.qzeros": "model-00001-of-00003.safetensors",
484
+ "model.layers.6.attention.wo.scales": "model-00001-of-00003.safetensors",
485
+ "model.layers.6.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
486
+ "model.layers.6.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
487
+ "model.layers.6.attention.wqkv.scales": "model-00001-of-00003.safetensors",
488
+ "model.layers.6.attention_norm.weight": "model-00001-of-00003.safetensors",
489
+ "model.layers.6.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
490
+ "model.layers.6.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
491
+ "model.layers.6.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
492
+ "model.layers.6.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
493
+ "model.layers.6.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
494
+ "model.layers.6.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
495
+ "model.layers.6.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
496
+ "model.layers.6.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
497
+ "model.layers.6.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
498
+ "model.layers.6.ffn_norm.weight": "model-00001-of-00003.safetensors",
499
+ "model.layers.7.attention.wo.qweight": "model-00001-of-00003.safetensors",
500
+ "model.layers.7.attention.wo.qzeros": "model-00001-of-00003.safetensors",
501
+ "model.layers.7.attention.wo.scales": "model-00001-of-00003.safetensors",
502
+ "model.layers.7.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
503
+ "model.layers.7.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
504
+ "model.layers.7.attention.wqkv.scales": "model-00001-of-00003.safetensors",
505
+ "model.layers.7.attention_norm.weight": "model-00001-of-00003.safetensors",
506
+ "model.layers.7.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
507
+ "model.layers.7.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
508
+ "model.layers.7.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
509
+ "model.layers.7.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
510
+ "model.layers.7.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
511
+ "model.layers.7.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
512
+ "model.layers.7.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
513
+ "model.layers.7.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
514
+ "model.layers.7.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
515
+ "model.layers.7.ffn_norm.weight": "model-00001-of-00003.safetensors",
516
+ "model.layers.8.attention.wo.qweight": "model-00001-of-00003.safetensors",
517
+ "model.layers.8.attention.wo.qzeros": "model-00001-of-00003.safetensors",
518
+ "model.layers.8.attention.wo.scales": "model-00001-of-00003.safetensors",
519
+ "model.layers.8.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
520
+ "model.layers.8.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
521
+ "model.layers.8.attention.wqkv.scales": "model-00001-of-00003.safetensors",
522
+ "model.layers.8.attention_norm.weight": "model-00001-of-00003.safetensors",
523
+ "model.layers.8.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
524
+ "model.layers.8.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
525
+ "model.layers.8.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
526
+ "model.layers.8.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
527
+ "model.layers.8.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
528
+ "model.layers.8.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
529
+ "model.layers.8.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
530
+ "model.layers.8.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
531
+ "model.layers.8.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
532
+ "model.layers.8.ffn_norm.weight": "model-00001-of-00003.safetensors",
533
+ "model.layers.9.attention.wo.qweight": "model-00001-of-00003.safetensors",
534
+ "model.layers.9.attention.wo.qzeros": "model-00001-of-00003.safetensors",
535
+ "model.layers.9.attention.wo.scales": "model-00001-of-00003.safetensors",
536
+ "model.layers.9.attention.wqkv.qweight": "model-00001-of-00003.safetensors",
537
+ "model.layers.9.attention.wqkv.qzeros": "model-00001-of-00003.safetensors",
538
+ "model.layers.9.attention.wqkv.scales": "model-00001-of-00003.safetensors",
539
+ "model.layers.9.attention_norm.weight": "model-00001-of-00003.safetensors",
540
+ "model.layers.9.feed_forward.w1.qweight": "model-00001-of-00003.safetensors",
541
+ "model.layers.9.feed_forward.w1.qzeros": "model-00001-of-00003.safetensors",
542
+ "model.layers.9.feed_forward.w1.scales": "model-00001-of-00003.safetensors",
543
+ "model.layers.9.feed_forward.w2.qweight": "model-00001-of-00003.safetensors",
544
+ "model.layers.9.feed_forward.w2.qzeros": "model-00001-of-00003.safetensors",
545
+ "model.layers.9.feed_forward.w2.scales": "model-00001-of-00003.safetensors",
546
+ "model.layers.9.feed_forward.w3.qweight": "model-00001-of-00003.safetensors",
547
+ "model.layers.9.feed_forward.w3.qzeros": "model-00001-of-00003.safetensors",
548
+ "model.layers.9.feed_forward.w3.scales": "model-00001-of-00003.safetensors",
549
+ "model.layers.9.ffn_norm.weight": "model-00001-of-00003.safetensors",
550
+ "model.norm.weight": "model-00003-of-00003.safetensors",
551
+ "model.tok_embeddings.weight": "model-00001-of-00003.safetensors",
552
+ "output.weight": "model-00003-of-00003.safetensors"
553
+ }
554
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,554 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5142749184
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
7
+ "model.layers.0.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.0.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.0.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.0.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.0.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.0.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.1.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.1.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.1.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.1.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.1.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.1.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.1.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.1.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.1.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.1.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.1.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.1.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.10.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.10.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.10.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.10.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.10.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.10.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.10.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
47
+ "model.layers.10.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.10.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.10.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.10.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.10.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.10.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.10.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.10.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.10.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.10.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.11.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.11.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.11.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.11.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.11.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.11.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.11.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.11.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.11.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.11.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.11.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.11.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.11.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.11.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.11.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.11.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.11.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.12.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.12.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.12.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.12.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.12.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.12.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.12.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.12.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.12.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.12.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.12.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.12.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.12.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.12.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.12.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.12.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.12.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.13.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.13.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.13.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.13.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.13.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.13.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.13.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.13.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.13.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.13.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.13.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.13.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.13.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.13.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.13.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.13.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.13.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.14.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.14.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.14.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.14.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.14.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.14.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.14.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.14.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.14.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.14.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.14.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.14.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.14.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.14.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.14.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.14.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.14.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.15.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.15.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.15.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.15.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.15.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.15.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.15.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.15.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.15.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.15.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.15.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.15.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.15.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.15.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.15.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.15.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.15.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.16.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.16.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.16.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.16.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.16.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.16.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.16.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.16.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.16.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.16.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.16.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.16.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.16.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.16.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.16.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.16.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.16.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.17.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.17.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.17.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.17.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.17.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.17.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.17.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.17.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.17.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.17.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.17.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.17.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.17.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.17.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.17.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.17.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.17.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.18.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.18.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.18.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.18.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.18.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.18.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.18.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.18.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.18.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.18.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.18.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.18.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.18.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.18.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.18.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.18.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.18.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.19.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.19.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.19.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.19.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.19.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.19.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.19.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.19.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.19.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.19.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.19.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.19.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.19.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.19.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.19.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.19.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.19.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.2.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
211
+ "model.layers.2.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
212
+ "model.layers.2.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
213
+ "model.layers.2.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
214
+ "model.layers.2.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
215
+ "model.layers.2.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.2.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.2.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.2.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.2.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.2.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.2.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.2.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.2.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.2.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
225
+ "model.layers.2.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
226
+ "model.layers.2.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
227
+ "model.layers.20.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.20.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.20.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.20.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.20.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.20.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.20.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.20.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.20.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.20.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.20.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.20.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
239
+ "model.layers.20.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
240
+ "model.layers.20.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
241
+ "model.layers.20.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
242
+ "model.layers.20.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
243
+ "model.layers.20.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
244
+ "model.layers.21.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
245
+ "model.layers.21.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
246
+ "model.layers.21.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
247
+ "model.layers.21.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
248
+ "model.layers.21.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
249
+ "model.layers.21.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
250
+ "model.layers.21.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.21.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.21.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
253
+ "model.layers.21.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.21.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.21.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.21.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.21.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.21.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
259
+ "model.layers.21.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
260
+ "model.layers.21.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.layers.22.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
262
+ "model.layers.22.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
263
+ "model.layers.22.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
264
+ "model.layers.22.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
265
+ "model.layers.22.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
266
+ "model.layers.22.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
267
+ "model.layers.22.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
268
+ "model.layers.22.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
269
+ "model.layers.22.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
270
+ "model.layers.22.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
271
+ "model.layers.22.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
272
+ "model.layers.22.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
273
+ "model.layers.22.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
274
+ "model.layers.22.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
275
+ "model.layers.22.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
276
+ "model.layers.22.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
277
+ "model.layers.22.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
278
+ "model.layers.23.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
279
+ "model.layers.23.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
280
+ "model.layers.23.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
281
+ "model.layers.23.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
282
+ "model.layers.23.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
283
+ "model.layers.23.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
284
+ "model.layers.23.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
285
+ "model.layers.23.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
286
+ "model.layers.23.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
287
+ "model.layers.23.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
288
+ "model.layers.23.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
289
+ "model.layers.23.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
290
+ "model.layers.23.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
291
+ "model.layers.23.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
292
+ "model.layers.23.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
293
+ "model.layers.23.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
294
+ "model.layers.23.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
295
+ "model.layers.24.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
296
+ "model.layers.24.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
297
+ "model.layers.24.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
298
+ "model.layers.24.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
299
+ "model.layers.24.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
300
+ "model.layers.24.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
301
+ "model.layers.24.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
302
+ "model.layers.24.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
303
+ "model.layers.24.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
304
+ "model.layers.24.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
305
+ "model.layers.24.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
306
+ "model.layers.24.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
307
+ "model.layers.24.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
308
+ "model.layers.24.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
309
+ "model.layers.24.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
310
+ "model.layers.24.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
311
+ "model.layers.24.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
312
+ "model.layers.25.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
313
+ "model.layers.25.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
314
+ "model.layers.25.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
315
+ "model.layers.25.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
316
+ "model.layers.25.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
317
+ "model.layers.25.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
318
+ "model.layers.25.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
319
+ "model.layers.25.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
320
+ "model.layers.25.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
321
+ "model.layers.25.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
322
+ "model.layers.25.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
323
+ "model.layers.25.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
324
+ "model.layers.25.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
325
+ "model.layers.25.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
326
+ "model.layers.25.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
327
+ "model.layers.25.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
328
+ "model.layers.25.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
329
+ "model.layers.26.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
330
+ "model.layers.26.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
331
+ "model.layers.26.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
332
+ "model.layers.26.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
333
+ "model.layers.26.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
334
+ "model.layers.26.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
335
+ "model.layers.26.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
336
+ "model.layers.26.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
337
+ "model.layers.26.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
338
+ "model.layers.26.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
339
+ "model.layers.26.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
340
+ "model.layers.26.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
341
+ "model.layers.26.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
342
+ "model.layers.26.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
343
+ "model.layers.26.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
344
+ "model.layers.26.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
345
+ "model.layers.26.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
346
+ "model.layers.27.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
347
+ "model.layers.27.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
348
+ "model.layers.27.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
349
+ "model.layers.27.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
350
+ "model.layers.27.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
351
+ "model.layers.27.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
352
+ "model.layers.27.attention_norm.weight": "pytorch_model-00002-of-00003.bin",
353
+ "model.layers.27.feed_forward.w1.qweight": "pytorch_model-00002-of-00003.bin",
354
+ "model.layers.27.feed_forward.w1.qzeros": "pytorch_model-00002-of-00003.bin",
355
+ "model.layers.27.feed_forward.w1.scales": "pytorch_model-00002-of-00003.bin",
356
+ "model.layers.27.feed_forward.w2.qweight": "pytorch_model-00002-of-00003.bin",
357
+ "model.layers.27.feed_forward.w2.qzeros": "pytorch_model-00002-of-00003.bin",
358
+ "model.layers.27.feed_forward.w2.scales": "pytorch_model-00002-of-00003.bin",
359
+ "model.layers.27.feed_forward.w3.qweight": "pytorch_model-00002-of-00003.bin",
360
+ "model.layers.27.feed_forward.w3.qzeros": "pytorch_model-00002-of-00003.bin",
361
+ "model.layers.27.feed_forward.w3.scales": "pytorch_model-00002-of-00003.bin",
362
+ "model.layers.27.ffn_norm.weight": "pytorch_model-00002-of-00003.bin",
363
+ "model.layers.28.attention.wo.qweight": "pytorch_model-00002-of-00003.bin",
364
+ "model.layers.28.attention.wo.qzeros": "pytorch_model-00002-of-00003.bin",
365
+ "model.layers.28.attention.wo.scales": "pytorch_model-00002-of-00003.bin",
366
+ "model.layers.28.attention.wqkv.qweight": "pytorch_model-00002-of-00003.bin",
367
+ "model.layers.28.attention.wqkv.qzeros": "pytorch_model-00002-of-00003.bin",
368
+ "model.layers.28.attention.wqkv.scales": "pytorch_model-00002-of-00003.bin",
369
+ "model.layers.28.attention_norm.weight": "pytorch_model-00003-of-00003.bin",
370
+ "model.layers.28.feed_forward.w1.qweight": "pytorch_model-00003-of-00003.bin",
371
+ "model.layers.28.feed_forward.w1.qzeros": "pytorch_model-00003-of-00003.bin",
372
+ "model.layers.28.feed_forward.w1.scales": "pytorch_model-00003-of-00003.bin",
373
+ "model.layers.28.feed_forward.w2.qweight": "pytorch_model-00003-of-00003.bin",
374
+ "model.layers.28.feed_forward.w2.qzeros": "pytorch_model-00003-of-00003.bin",
375
+ "model.layers.28.feed_forward.w2.scales": "pytorch_model-00003-of-00003.bin",
376
+ "model.layers.28.feed_forward.w3.qweight": "pytorch_model-00003-of-00003.bin",
377
+ "model.layers.28.feed_forward.w3.qzeros": "pytorch_model-00003-of-00003.bin",
378
+ "model.layers.28.feed_forward.w3.scales": "pytorch_model-00003-of-00003.bin",
379
+ "model.layers.28.ffn_norm.weight": "pytorch_model-00003-of-00003.bin",
380
+ "model.layers.29.attention.wo.qweight": "pytorch_model-00003-of-00003.bin",
381
+ "model.layers.29.attention.wo.qzeros": "pytorch_model-00003-of-00003.bin",
382
+ "model.layers.29.attention.wo.scales": "pytorch_model-00003-of-00003.bin",
383
+ "model.layers.29.attention.wqkv.qweight": "pytorch_model-00003-of-00003.bin",
384
+ "model.layers.29.attention.wqkv.qzeros": "pytorch_model-00003-of-00003.bin",
385
+ "model.layers.29.attention.wqkv.scales": "pytorch_model-00003-of-00003.bin",
386
+ "model.layers.29.attention_norm.weight": "pytorch_model-00003-of-00003.bin",
387
+ "model.layers.29.feed_forward.w1.qweight": "pytorch_model-00003-of-00003.bin",
388
+ "model.layers.29.feed_forward.w1.qzeros": "pytorch_model-00003-of-00003.bin",
389
+ "model.layers.29.feed_forward.w1.scales": "pytorch_model-00003-of-00003.bin",
390
+ "model.layers.29.feed_forward.w2.qweight": "pytorch_model-00003-of-00003.bin",
391
+ "model.layers.29.feed_forward.w2.qzeros": "pytorch_model-00003-of-00003.bin",
392
+ "model.layers.29.feed_forward.w2.scales": "pytorch_model-00003-of-00003.bin",
393
+ "model.layers.29.feed_forward.w3.qweight": "pytorch_model-00003-of-00003.bin",
394
+ "model.layers.29.feed_forward.w3.qzeros": "pytorch_model-00003-of-00003.bin",
395
+ "model.layers.29.feed_forward.w3.scales": "pytorch_model-00003-of-00003.bin",
396
+ "model.layers.29.ffn_norm.weight": "pytorch_model-00003-of-00003.bin",
397
+ "model.layers.3.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.3.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.3.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.3.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.3.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.3.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.3.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.3.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.3.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.3.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.3.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
408
+ "model.layers.3.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
409
+ "model.layers.3.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
410
+ "model.layers.3.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
411
+ "model.layers.3.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
412
+ "model.layers.3.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
413
+ "model.layers.3.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
414
+ "model.layers.30.attention.wo.qweight": "pytorch_model-00003-of-00003.bin",
415
+ "model.layers.30.attention.wo.qzeros": "pytorch_model-00003-of-00003.bin",
416
+ "model.layers.30.attention.wo.scales": "pytorch_model-00003-of-00003.bin",
417
+ "model.layers.30.attention.wqkv.qweight": "pytorch_model-00003-of-00003.bin",
418
+ "model.layers.30.attention.wqkv.qzeros": "pytorch_model-00003-of-00003.bin",
419
+ "model.layers.30.attention.wqkv.scales": "pytorch_model-00003-of-00003.bin",
420
+ "model.layers.30.attention_norm.weight": "pytorch_model-00003-of-00003.bin",
421
+ "model.layers.30.feed_forward.w1.qweight": "pytorch_model-00003-of-00003.bin",
422
+ "model.layers.30.feed_forward.w1.qzeros": "pytorch_model-00003-of-00003.bin",
423
+ "model.layers.30.feed_forward.w1.scales": "pytorch_model-00003-of-00003.bin",
424
+ "model.layers.30.feed_forward.w2.qweight": "pytorch_model-00003-of-00003.bin",
425
+ "model.layers.30.feed_forward.w2.qzeros": "pytorch_model-00003-of-00003.bin",
426
+ "model.layers.30.feed_forward.w2.scales": "pytorch_model-00003-of-00003.bin",
427
+ "model.layers.30.feed_forward.w3.qweight": "pytorch_model-00003-of-00003.bin",
428
+ "model.layers.30.feed_forward.w3.qzeros": "pytorch_model-00003-of-00003.bin",
429
+ "model.layers.30.feed_forward.w3.scales": "pytorch_model-00003-of-00003.bin",
430
+ "model.layers.30.ffn_norm.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.layers.31.attention.wo.qweight": "pytorch_model-00003-of-00003.bin",
432
+ "model.layers.31.attention.wo.qzeros": "pytorch_model-00003-of-00003.bin",
433
+ "model.layers.31.attention.wo.scales": "pytorch_model-00003-of-00003.bin",
434
+ "model.layers.31.attention.wqkv.qweight": "pytorch_model-00003-of-00003.bin",
435
+ "model.layers.31.attention.wqkv.qzeros": "pytorch_model-00003-of-00003.bin",
436
+ "model.layers.31.attention.wqkv.scales": "pytorch_model-00003-of-00003.bin",
437
+ "model.layers.31.attention_norm.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.layers.31.feed_forward.w1.qweight": "pytorch_model-00003-of-00003.bin",
439
+ "model.layers.31.feed_forward.w1.qzeros": "pytorch_model-00003-of-00003.bin",
440
+ "model.layers.31.feed_forward.w1.scales": "pytorch_model-00003-of-00003.bin",
441
+ "model.layers.31.feed_forward.w2.qweight": "pytorch_model-00003-of-00003.bin",
442
+ "model.layers.31.feed_forward.w2.qzeros": "pytorch_model-00003-of-00003.bin",
443
+ "model.layers.31.feed_forward.w2.scales": "pytorch_model-00003-of-00003.bin",
444
+ "model.layers.31.feed_forward.w3.qweight": "pytorch_model-00003-of-00003.bin",
445
+ "model.layers.31.feed_forward.w3.qzeros": "pytorch_model-00003-of-00003.bin",
446
+ "model.layers.31.feed_forward.w3.scales": "pytorch_model-00003-of-00003.bin",
447
+ "model.layers.31.ffn_norm.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.layers.4.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
449
+ "model.layers.4.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
450
+ "model.layers.4.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
451
+ "model.layers.4.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
452
+ "model.layers.4.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
453
+ "model.layers.4.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
454
+ "model.layers.4.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
455
+ "model.layers.4.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
456
+ "model.layers.4.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
457
+ "model.layers.4.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
458
+ "model.layers.4.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
459
+ "model.layers.4.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
460
+ "model.layers.4.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
461
+ "model.layers.4.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
462
+ "model.layers.4.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
463
+ "model.layers.4.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
464
+ "model.layers.4.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
465
+ "model.layers.5.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
466
+ "model.layers.5.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
467
+ "model.layers.5.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
468
+ "model.layers.5.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
469
+ "model.layers.5.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
470
+ "model.layers.5.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
471
+ "model.layers.5.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
472
+ "model.layers.5.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
473
+ "model.layers.5.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
474
+ "model.layers.5.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
475
+ "model.layers.5.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
476
+ "model.layers.5.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
477
+ "model.layers.5.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
478
+ "model.layers.5.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
479
+ "model.layers.5.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
480
+ "model.layers.5.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
481
+ "model.layers.5.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
482
+ "model.layers.6.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
483
+ "model.layers.6.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
484
+ "model.layers.6.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
485
+ "model.layers.6.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
486
+ "model.layers.6.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
487
+ "model.layers.6.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
488
+ "model.layers.6.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
489
+ "model.layers.6.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
490
+ "model.layers.6.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
491
+ "model.layers.6.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
492
+ "model.layers.6.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
493
+ "model.layers.6.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
494
+ "model.layers.6.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
495
+ "model.layers.6.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
496
+ "model.layers.6.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
497
+ "model.layers.6.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
498
+ "model.layers.6.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
499
+ "model.layers.7.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
500
+ "model.layers.7.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
501
+ "model.layers.7.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
502
+ "model.layers.7.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
503
+ "model.layers.7.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
504
+ "model.layers.7.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
505
+ "model.layers.7.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
506
+ "model.layers.7.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
507
+ "model.layers.7.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
508
+ "model.layers.7.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
509
+ "model.layers.7.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
510
+ "model.layers.7.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
511
+ "model.layers.7.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
512
+ "model.layers.7.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
513
+ "model.layers.7.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
514
+ "model.layers.7.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
515
+ "model.layers.7.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
516
+ "model.layers.8.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
517
+ "model.layers.8.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
518
+ "model.layers.8.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
519
+ "model.layers.8.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
520
+ "model.layers.8.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
521
+ "model.layers.8.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
522
+ "model.layers.8.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
523
+ "model.layers.8.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
524
+ "model.layers.8.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
525
+ "model.layers.8.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
526
+ "model.layers.8.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
527
+ "model.layers.8.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
528
+ "model.layers.8.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
529
+ "model.layers.8.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
530
+ "model.layers.8.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
531
+ "model.layers.8.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
532
+ "model.layers.8.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
533
+ "model.layers.9.attention.wo.qweight": "pytorch_model-00001-of-00003.bin",
534
+ "model.layers.9.attention.wo.qzeros": "pytorch_model-00001-of-00003.bin",
535
+ "model.layers.9.attention.wo.scales": "pytorch_model-00001-of-00003.bin",
536
+ "model.layers.9.attention.wqkv.qweight": "pytorch_model-00001-of-00003.bin",
537
+ "model.layers.9.attention.wqkv.qzeros": "pytorch_model-00001-of-00003.bin",
538
+ "model.layers.9.attention.wqkv.scales": "pytorch_model-00001-of-00003.bin",
539
+ "model.layers.9.attention_norm.weight": "pytorch_model-00001-of-00003.bin",
540
+ "model.layers.9.feed_forward.w1.qweight": "pytorch_model-00001-of-00003.bin",
541
+ "model.layers.9.feed_forward.w1.qzeros": "pytorch_model-00001-of-00003.bin",
542
+ "model.layers.9.feed_forward.w1.scales": "pytorch_model-00001-of-00003.bin",
543
+ "model.layers.9.feed_forward.w2.qweight": "pytorch_model-00001-of-00003.bin",
544
+ "model.layers.9.feed_forward.w2.qzeros": "pytorch_model-00001-of-00003.bin",
545
+ "model.layers.9.feed_forward.w2.scales": "pytorch_model-00001-of-00003.bin",
546
+ "model.layers.9.feed_forward.w3.qweight": "pytorch_model-00001-of-00003.bin",
547
+ "model.layers.9.feed_forward.w3.qzeros": "pytorch_model-00001-of-00003.bin",
548
+ "model.layers.9.feed_forward.w3.scales": "pytorch_model-00001-of-00003.bin",
549
+ "model.layers.9.ffn_norm.weight": "pytorch_model-00001-of-00003.bin",
550
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
551
+ "model.tok_embeddings.weight": "pytorch_model-00001-of-00003.bin",
552
+ "output.weight": "pytorch_model-00003-of-00003.bin"
553
+ }
554
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<|im_start|>",
78
+ "<|im_end|>",
79
+ "<|action_start|>",
80
+ "<|action_end|>",
81
+ "<|interpreter|>",
82
+ "<|plugin|>"
83
+ ],
84
+ "auto_map": {
85
+ "AutoTokenizer": [
86
+ "tokenization_internlm2.InternLM2Tokenizer",
87
+ null
88
+ ]
89
+ },
90
+ "bos_token": "<s>",
91
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
92
+ "clean_up_tokenization_spaces": false,
93
+ "eos_token": "</s>",
94
+ "model_max_length": 1000000000000000019884624838656,
95
+ "pad_token": "</s>",
96
+ "tokenizer_class": "InternLM2Tokenizer",
97
+ "unk_token": "<unk>"
98
+ }