Hugging Face's logo

adamo1139
/
Qwen2.5-7B-Instruct-FP8-Dynamic_FP16-Vision

Safetensors
qwen2_vl
compressed-tensors
Model card Files Community
adamo1139 commited on
Commit
e0b5893
•
1 Parent(s): f8143ba

Upload 14 files

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +16 -0
  3. chat_template.json +3 -0
  4. config.json +219 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00003.safetensors +3 -0
  8. model-00002-of-00003.safetensors +3 -0
  9. model-00003-of-00003.safetensors +3 -0
  10. model.safetensors.index.json +933 -0
  11. preprocessor_config.json +29 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +144 -0
  15. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "adamo1139/Qwen2.5-7B-Instruct-FP8-Dynamic_FP16-Vision",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "quantization_config": {
21
+ "config_groups": {
22
+ "group_0": {
23
+ "input_activations": {
24
+ "actorder": null,
25
+ "block_structure": null,
26
+ "dynamic": true,
27
+ "group_size": null,
28
+ "num_bits": 8,
29
+ "observer": null,
30
+ "observer_kwargs": {},
31
+ "strategy": "token",
32
+ "symmetric": true,
33
+ "type": "float"
34
+ },
35
+ "output_activations": null,
36
+ "targets": [
37
+ "Linear"
38
+ ],
39
+ "weights": {
40
+ "actorder": null,
41
+ "block_structure": null,
42
+ "dynamic": false,
43
+ "group_size": null,
44
+ "num_bits": 8,
45
+ "observer": "minmax",
46
+ "observer_kwargs": {},
47
+ "strategy": "channel",
48
+ "symmetric": true,
49
+ "type": "float"
50
+ }
51
+ }
52
+ },
53
+ "format": "float-quantized",
54
+ "global_compression_ratio": 1.220698132330407,
55
+ "ignore": [
56
+ "visual.blocks.0.attn.qkv",
57
+ "visual.blocks.0.attn.proj",
58
+ "visual.blocks.0.mlp.fc1",
59
+ "visual.blocks.0.mlp.fc2",
60
+ "visual.blocks.1.attn.qkv",
61
+ "visual.blocks.1.attn.proj",
62
+ "visual.blocks.1.mlp.fc1",
63
+ "visual.blocks.1.mlp.fc2",
64
+ "visual.blocks.2.attn.qkv",
65
+ "visual.blocks.2.attn.proj",
66
+ "visual.blocks.2.mlp.fc1",
67
+ "visual.blocks.2.mlp.fc2",
68
+ "visual.blocks.3.attn.qkv",
69
+ "visual.blocks.3.attn.proj",
70
+ "visual.blocks.3.mlp.fc1",
71
+ "visual.blocks.3.mlp.fc2",
72
+ "visual.blocks.4.attn.qkv",
73
+ "visual.blocks.4.attn.proj",
74
+ "visual.blocks.4.mlp.fc1",
75
+ "visual.blocks.4.mlp.fc2",
76
+ "visual.blocks.5.attn.qkv",
77
+ "visual.blocks.5.attn.proj",
78
+ "visual.blocks.5.mlp.fc1",
79
+ "visual.blocks.5.mlp.fc2",
80
+ "visual.blocks.6.attn.qkv",
81
+ "visual.blocks.6.attn.proj",
82
+ "visual.blocks.6.mlp.fc1",
83
+ "visual.blocks.6.mlp.fc2",
84
+ "visual.blocks.7.attn.qkv",
85
+ "visual.blocks.7.attn.proj",
86
+ "visual.blocks.7.mlp.fc1",
87
+ "visual.blocks.7.mlp.fc2",
88
+ "visual.blocks.8.attn.qkv",
89
+ "visual.blocks.8.attn.proj",
90
+ "visual.blocks.8.mlp.fc1",
91
+ "visual.blocks.8.mlp.fc2",
92
+ "visual.blocks.9.attn.qkv",
93
+ "visual.blocks.9.attn.proj",
94
+ "visual.blocks.9.mlp.fc1",
95
+ "visual.blocks.9.mlp.fc2",
96
+ "visual.blocks.10.attn.qkv",
97
+ "visual.blocks.10.attn.proj",
98
+ "visual.blocks.10.mlp.fc1",
99
+ "visual.blocks.10.mlp.fc2",
100
+ "visual.blocks.11.attn.qkv",
101
+ "visual.blocks.11.attn.proj",
102
+ "visual.blocks.11.mlp.fc1",
103
+ "visual.blocks.11.mlp.fc2",
104
+ "visual.blocks.12.attn.qkv",
105
+ "visual.blocks.12.attn.proj",
106
+ "visual.blocks.12.mlp.fc1",
107
+ "visual.blocks.12.mlp.fc2",
108
+ "visual.blocks.13.attn.qkv",
109
+ "visual.blocks.13.attn.proj",
110
+ "visual.blocks.13.mlp.fc1",
111
+ "visual.blocks.13.mlp.fc2",
112
+ "visual.blocks.14.attn.qkv",
113
+ "visual.blocks.14.attn.proj",
114
+ "visual.blocks.14.mlp.fc1",
115
+ "visual.blocks.14.mlp.fc2",
116
+ "visual.blocks.15.attn.qkv",
117
+ "visual.blocks.15.attn.proj",
118
+ "visual.blocks.15.mlp.fc1",
119
+ "visual.blocks.15.mlp.fc2",
120
+ "visual.blocks.16.attn.qkv",
121
+ "visual.blocks.16.attn.proj",
122
+ "visual.blocks.16.mlp.fc1",
123
+ "visual.blocks.16.mlp.fc2",
124
+ "visual.blocks.17.attn.qkv",
125
+ "visual.blocks.17.attn.proj",
126
+ "visual.blocks.17.mlp.fc1",
127
+ "visual.blocks.17.mlp.fc2",
128
+ "visual.blocks.18.attn.qkv",
129
+ "visual.blocks.18.attn.proj",
130
+ "visual.blocks.18.mlp.fc1",
131
+ "visual.blocks.18.mlp.fc2",
132
+ "visual.blocks.19.attn.qkv",
133
+ "visual.blocks.19.attn.proj",
134
+ "visual.blocks.19.mlp.fc1",
135
+ "visual.blocks.19.mlp.fc2",
136
+ "visual.blocks.20.attn.qkv",
137
+ "visual.blocks.20.attn.proj",
138
+ "visual.blocks.20.mlp.fc1",
139
+ "visual.blocks.20.mlp.fc2",
140
+ "visual.blocks.21.attn.qkv",
141
+ "visual.blocks.21.attn.proj",
142
+ "visual.blocks.21.mlp.fc1",
143
+ "visual.blocks.21.mlp.fc2",
144
+ "visual.blocks.22.attn.qkv",
145
+ "visual.blocks.22.attn.proj",
146
+ "visual.blocks.22.mlp.fc1",
147
+ "visual.blocks.22.mlp.fc2",
148
+ "visual.blocks.23.attn.qkv",
149
+ "visual.blocks.23.attn.proj",
150
+ "visual.blocks.23.mlp.fc1",
151
+ "visual.blocks.23.mlp.fc2",
152
+ "visual.blocks.24.attn.qkv",
153
+ "visual.blocks.24.attn.proj",
154
+ "visual.blocks.24.mlp.fc1",
155
+ "visual.blocks.24.mlp.fc2",
156
+ "visual.blocks.25.attn.qkv",
157
+ "visual.blocks.25.attn.proj",
158
+ "visual.blocks.25.mlp.fc1",
159
+ "visual.blocks.25.mlp.fc2",
160
+ "visual.blocks.26.attn.qkv",
161
+ "visual.blocks.26.attn.proj",
162
+ "visual.blocks.26.mlp.fc1",
163
+ "visual.blocks.26.mlp.fc2",
164
+ "visual.blocks.27.attn.qkv",
165
+ "visual.blocks.27.attn.proj",
166
+ "visual.blocks.27.mlp.fc1",
167
+ "visual.blocks.27.mlp.fc2",
168
+ "visual.blocks.28.attn.qkv",
169
+ "visual.blocks.28.attn.proj",
170
+ "visual.blocks.28.mlp.fc1",
171
+ "visual.blocks.28.mlp.fc2",
172
+ "visual.blocks.29.attn.qkv",
173
+ "visual.blocks.29.attn.proj",
174
+ "visual.blocks.29.mlp.fc1",
175
+ "visual.blocks.29.mlp.fc2",
176
+ "visual.blocks.30.attn.qkv",
177
+ "visual.blocks.30.attn.proj",
178
+ "visual.blocks.30.mlp.fc1",
179
+ "visual.blocks.30.mlp.fc2",
180
+ "visual.blocks.31.attn.qkv",
181
+ "visual.blocks.31.attn.proj",
182
+ "visual.blocks.31.mlp.fc1",
183
+ "visual.blocks.31.mlp.fc2",
184
+ "visual.merger.mlp.0",
185
+ "visual.merger.mlp.2",
186
+ "lm_head"
187
+ ],
188
+ "kv_cache_scheme": null,
189
+ "quant_method": "compressed-tensors",
190
+ "quantization_status": "compressed"
191
+ },
192
+ "rms_norm_eps": 1e-06,
193
+ "rope_scaling": {
194
+ "mrope_section": [
195
+ 16,
196
+ 24,
197
+ 24
198
+ ],
199
+ "rope_type": "default",
200
+ "type": "default"
201
+ },
202
+ "rope_theta": 1000000.0,
203
+ "sliding_window": 4096,
204
+ "tie_word_embeddings": false,
205
+ "torch_dtype": "bfloat16",
206
+ "transformers_version": "4.46.0.dev0",
207
+ "use_cache": true,
208
+ "use_sliding_window": false,
209
+ "video_token_id": 151656,
210
+ "vision_config": {
211
+ "in_chans": 3,
212
+ "model_type": "qwen2_vl",
213
+ "spatial_patch_size": 14
214
+ },
215
+ "vision_end_token_id": 151653,
216
+ "vision_start_token_id": 151652,
217
+ "vision_token_id": 151654,
218
+ "vocab_size": 152064
219
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.46.0.dev0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5a686c2b56588155c65b173ef7fd6a2fdc5e350942c32e9a60857630933ee3
3
+ size 4938519208
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2df119f1ba538ce27b6bfb6c4b3cfcca9d618c5cf37dfae72df81767fc1f98
3
+ size 4031832312
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76ec4dc2e7c0dcbe3432e58fae08e62204a2ef2323069d85c8fa0affb87332a
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,933 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10060243968
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
49
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
51
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
53
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
55
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
57
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
59
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
60
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
62
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
63
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
65
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
68
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
70
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
72
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
74
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
76
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
78
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
79
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
81
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
82
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
84
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
87
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
89
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
91
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
93
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
95
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
97
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
98
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
100
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
101
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
103
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
106
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
108
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
110
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
112
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
114
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
116
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
117
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
119
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
120
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
122
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
125
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
127
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
129
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
131
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
133
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
135
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
136
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
138
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
139
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
141
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
144
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
146
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
148
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
150
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
152
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
154
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
155
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
157
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
158
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
160
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
163
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
165
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
167
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
169
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
171
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
173
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
174
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
176
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
177
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
179
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
182
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
184
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
186
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
188
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
190
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
192
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
193
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
195
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
196
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
198
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
201
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
203
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
205
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
207
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
209
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
211
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
212
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
214
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
215
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
217
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
220
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
222
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
224
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
226
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
228
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
230
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
231
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
233
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
234
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
236
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
239
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
241
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
242
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
243
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
245
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
247
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
249
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
250
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
252
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
253
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
255
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
258
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
260
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
262
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
263
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
264
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
265
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
266
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
267
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
268
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
269
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
270
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
271
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
272
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
274
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
277
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
279
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
281
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
283
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
285
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
286
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
287
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
288
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
289
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
290
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
291
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
292
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
293
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
294
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
296
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
297
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
298
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
300
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
302
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
304
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
305
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
306
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
307
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
309
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
310
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
312
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
314
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
315
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
316
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
317
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
318
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
319
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
320
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
321
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
322
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
323
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
324
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
325
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
326
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
327
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
328
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
329
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
330
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
331
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
332
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
334
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
336
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
337
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
338
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
339
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
340
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
342
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
343
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
344
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
345
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
346
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
347
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
348
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
349
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
350
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
351
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
352
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
353
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
354
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
355
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
356
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
357
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
358
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
359
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
360
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
361
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
362
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
363
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
364
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
365
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
366
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
367
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
368
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
369
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
370
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
371
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
372
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
373
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
374
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
375
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
376
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
377
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
378
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
379
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
380
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
381
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
382
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
383
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
384
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
385
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
386
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
387
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
388
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
389
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
390
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
391
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
392
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
393
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
394
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
395
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
396
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
397
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
398
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
399
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
400
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
401
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
402
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
403
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
404
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
405
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
406
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
407
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
408
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
409
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
410
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
411
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
412
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
413
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
414
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
415
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
416
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
417
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
418
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
419
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
420
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
421
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
422
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
423
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
424
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
425
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
426
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
427
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
428
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
429
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
430
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
431
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
432
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
433
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
434
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
435
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
436
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
437
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
438
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
439
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
440
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
441
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
442
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
443
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
444
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
445
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
446
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
447
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
448
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
449
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
450
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
451
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
452
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
453
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
454
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
455
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
456
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
457
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
458
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
459
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
460
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
461
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
462
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
463
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
464
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
465
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
466
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
467
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
468
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
469
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
470
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
471
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
472
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
473
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
474
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
475
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
476
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
477
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
478
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
479
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
480
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
481
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
482
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
483
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
484
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
485
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
486
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
487
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
488
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
489
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
490
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
491
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
492
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
493
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
494
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
495
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
496
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
497
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
498
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
499
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
500
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
501
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
502
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
503
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
504
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
505
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
506
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
507
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
508
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
509
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
510
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
511
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
512
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
513
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
514
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
515
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
516
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
517
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
518
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
519
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
520
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
521
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
522
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
523
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
524
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
525
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
526
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
527
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
528
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
529
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
530
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
531
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
532
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
533
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
534
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
535
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
536
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
537
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
538
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
539
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
540
+ "model.norm.weight": "model-00002-of-00003.safetensors",
541
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
542
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
543
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
544
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
545
+ "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
546
+ "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
547
+ "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
548
+ "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
549
+ "visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
550
+ "visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
551
+ "visual.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
552
+ "visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
553
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
554
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
555
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
556
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
557
+ "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
558
+ "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
559
+ "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
560
+ "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
561
+ "visual.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
562
+ "visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
563
+ "visual.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
564
+ "visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
565
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
566
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
567
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
568
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
569
+ "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
570
+ "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
571
+ "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
572
+ "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
573
+ "visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
574
+ "visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
575
+ "visual.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
576
+ "visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
577
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
578
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
579
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
580
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
581
+ "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
582
+ "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
583
+ "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
584
+ "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
585
+ "visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
586
+ "visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
587
+ "visual.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
588
+ "visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
589
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
590
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
591
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
592
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
593
+ "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
594
+ "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
595
+ "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
596
+ "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
597
+ "visual.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
598
+ "visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
599
+ "visual.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
600
+ "visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
601
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
602
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
603
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
604
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
605
+ "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
606
+ "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
607
+ "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
608
+ "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
609
+ "visual.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
610
+ "visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
611
+ "visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
612
+ "visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
613
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
614
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
615
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
616
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
617
+ "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
618
+ "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
619
+ "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
620
+ "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
621
+ "visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
622
+ "visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
623
+ "visual.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
624
+ "visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
625
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
626
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
627
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
628
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
629
+ "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
630
+ "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
631
+ "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
632
+ "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
633
+ "visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
634
+ "visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
635
+ "visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
636
+ "visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
637
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
638
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
639
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
640
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
641
+ "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
642
+ "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
643
+ "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
644
+ "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
645
+ "visual.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
646
+ "visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
647
+ "visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
648
+ "visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
649
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
650
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
651
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
652
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
653
+ "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
654
+ "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
655
+ "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
656
+ "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
657
+ "visual.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
658
+ "visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
659
+ "visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
660
+ "visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
661
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
662
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
663
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
664
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
665
+ "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
666
+ "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
667
+ "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
668
+ "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
669
+ "visual.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
670
+ "visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
671
+ "visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
672
+ "visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
673
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
674
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
675
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
676
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
677
+ "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
678
+ "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
679
+ "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
680
+ "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
681
+ "visual.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
682
+ "visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
683
+ "visual.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
684
+ "visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
685
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
686
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
687
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
688
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
689
+ "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
690
+ "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
691
+ "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
692
+ "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
693
+ "visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
694
+ "visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
695
+ "visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
696
+ "visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
697
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
698
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
699
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
700
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
701
+ "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
702
+ "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
703
+ "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
704
+ "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
705
+ "visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
706
+ "visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
707
+ "visual.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
708
+ "visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
709
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
710
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
711
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
712
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
713
+ "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
714
+ "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
715
+ "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
716
+ "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
717
+ "visual.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
718
+ "visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
719
+ "visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
720
+ "visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
721
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
722
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
723
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
724
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
725
+ "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
726
+ "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
727
+ "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
728
+ "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
729
+ "visual.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
730
+ "visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
731
+ "visual.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
732
+ "visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
733
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
734
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
735
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
736
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
737
+ "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
738
+ "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
739
+ "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
740
+ "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
741
+ "visual.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
742
+ "visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
743
+ "visual.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
744
+ "visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
745
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
746
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
747
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
748
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
749
+ "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
750
+ "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
751
+ "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
752
+ "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
753
+ "visual.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
754
+ "visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
755
+ "visual.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
756
+ "visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
757
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
758
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
759
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
760
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
761
+ "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
762
+ "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
763
+ "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
764
+ "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
765
+ "visual.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
766
+ "visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
767
+ "visual.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
768
+ "visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
769
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
770
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
771
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
772
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
773
+ "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
774
+ "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
775
+ "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
776
+ "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
777
+ "visual.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
778
+ "visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
779
+ "visual.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
780
+ "visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
781
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00003.safetensors",
782
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00003.safetensors",
783
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00003.safetensors",
784
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00003.safetensors",
785
+ "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00003.safetensors",
786
+ "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00003.safetensors",
787
+ "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00003.safetensors",
788
+ "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00003.safetensors",
789
+ "visual.blocks.27.norm1.bias": "model-00001-of-00003.safetensors",
790
+ "visual.blocks.27.norm1.weight": "model-00001-of-00003.safetensors",
791
+ "visual.blocks.27.norm2.bias": "model-00001-of-00003.safetensors",
792
+ "visual.blocks.27.norm2.weight": "model-00001-of-00003.safetensors",
793
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00003.safetensors",
794
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00003.safetensors",
795
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00003.safetensors",
796
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00003.safetensors",
797
+ "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00003.safetensors",
798
+ "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00003.safetensors",
799
+ "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00003.safetensors",
800
+ "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00003.safetensors",
801
+ "visual.blocks.28.norm1.bias": "model-00001-of-00003.safetensors",
802
+ "visual.blocks.28.norm1.weight": "model-00001-of-00003.safetensors",
803
+ "visual.blocks.28.norm2.bias": "model-00001-of-00003.safetensors",
804
+ "visual.blocks.28.norm2.weight": "model-00001-of-00003.safetensors",
805
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00003.safetensors",
806
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00003.safetensors",
807
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00003.safetensors",
808
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00003.safetensors",
809
+ "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00003.safetensors",
810
+ "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00003.safetensors",
811
+ "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00003.safetensors",
812
+ "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00003.safetensors",
813
+ "visual.blocks.29.norm1.bias": "model-00001-of-00003.safetensors",
814
+ "visual.blocks.29.norm1.weight": "model-00001-of-00003.safetensors",
815
+ "visual.blocks.29.norm2.bias": "model-00001-of-00003.safetensors",
816
+ "visual.blocks.29.norm2.weight": "model-00001-of-00003.safetensors",
817
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
818
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
819
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
820
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
821
+ "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
822
+ "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
823
+ "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
824
+ "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
825
+ "visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
826
+ "visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
827
+ "visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
828
+ "visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
829
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00003.safetensors",
830
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00003.safetensors",
831
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00003.safetensors",
832
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00003.safetensors",
833
+ "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00003.safetensors",
834
+ "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00003.safetensors",
835
+ "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00003.safetensors",
836
+ "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00003.safetensors",
837
+ "visual.blocks.30.norm1.bias": "model-00001-of-00003.safetensors",
838
+ "visual.blocks.30.norm1.weight": "model-00001-of-00003.safetensors",
839
+ "visual.blocks.30.norm2.bias": "model-00001-of-00003.safetensors",
840
+ "visual.blocks.30.norm2.weight": "model-00001-of-00003.safetensors",
841
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00003.safetensors",
842
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00003.safetensors",
843
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00003.safetensors",
844
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00003.safetensors",
845
+ "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00003.safetensors",
846
+ "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00003.safetensors",
847
+ "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00003.safetensors",
848
+ "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00003.safetensors",
849
+ "visual.blocks.31.norm1.bias": "model-00001-of-00003.safetensors",
850
+ "visual.blocks.31.norm1.weight": "model-00001-of-00003.safetensors",
851
+ "visual.blocks.31.norm2.bias": "model-00001-of-00003.safetensors",
852
+ "visual.blocks.31.norm2.weight": "model-00001-of-00003.safetensors",
853
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
854
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
855
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
856
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
857
+ "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
858
+ "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
859
+ "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
860
+ "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
861
+ "visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
862
+ "visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
863
+ "visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
864
+ "visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
865
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
866
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
867
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
868
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
869
+ "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
870
+ "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
871
+ "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
872
+ "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
873
+ "visual.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
874
+ "visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
875
+ "visual.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
876
+ "visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
877
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
878
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
879
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
880
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
881
+ "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
882
+ "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
883
+ "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
884
+ "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
885
+ "visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
886
+ "visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
887
+ "visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
888
+ "visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
889
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
890
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
891
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
892
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
893
+ "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
894
+ "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
895
+ "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
896
+ "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
897
+ "visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
898
+ "visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
899
+ "visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
900
+ "visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
901
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
902
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
903
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
904
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
905
+ "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
906
+ "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
907
+ "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
908
+ "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
909
+ "visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
910
+ "visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
911
+ "visual.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
912
+ "visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
913
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
914
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
915
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
916
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
917
+ "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
918
+ "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
919
+ "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
920
+ "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
921
+ "visual.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
922
+ "visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
923
+ "visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
924
+ "visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
925
+ "visual.merger.ln_q.bias": "model-00001-of-00003.safetensors",
926
+ "visual.merger.ln_q.weight": "model-00001-of-00003.safetensors",
927
+ "visual.merger.mlp.0.bias": "model-00001-of-00003.safetensors",
928
+ "visual.merger.mlp.0.weight": "model-00001-of-00003.safetensors",
929
+ "visual.merger.mlp.2.bias": "model-00001-of-00003.safetensors",
930
+ "visual.merger.mlp.2.weight": "model-00001-of-00003.safetensors",
931
+ "visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors"
932
+ }
933
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff