Hugging Face's logo

mlx-community
/
Qwen2.5-VL-32B-Instruct-bf16

Image-Text-to-Text
Transformers
Safetensors
MLX
English
qwen2_5_vl
image-to-text
multimodal
conversational
text-generation-inference
Model card Files
xet
Community
1
prince-canuma commited on
Commit
34047c6
·
verified ·
1 Parent(s): 5f5b689

Upload folder using huggingface_hub

Browse files
Files changed (26) hide show
  1. .gitattributes +1 -0
  2. README.md +23 -0
  3. added_tokens.json +24 -0
  4. chat_template.json +3 -0
  5. config.json +180 -0
  6. generation_config.json +12 -0
  7. merges.txt +0 -0
  8. model-00001-of-00013.safetensors +3 -0
  9. model-00002-of-00013.safetensors +3 -0
  10. model-00003-of-00013.safetensors +3 -0
  11. model-00004-of-00013.safetensors +3 -0
  12. model-00005-of-00013.safetensors +3 -0
  13. model-00006-of-00013.safetensors +3 -0
  14. model-00007-of-00013.safetensors +3 -0
  15. model-00008-of-00013.safetensors +3 -0
  16. model-00009-of-00013.safetensors +3 -0
  17. model-00010-of-00013.safetensors +3 -0
  18. model-00011-of-00013.safetensors +3 -0
  19. model-00012-of-00013.safetensors +3 -0
  20. model-00013-of-00013.safetensors +3 -0
  21. model.safetensors.index.json +1168 -0
  22. preprocessor_config.json +29 -0
  23. special_tokens_map.json +31 -0
  24. tokenizer.json +3 -0
  25. tokenizer_config.json +209 -0
  26. 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
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ pipeline_tag: image-text-to-text
6
+ tags:
7
+ - multimodal
8
+ - mlx
9
+ library_name: transformers
10
+ ---
11
+
12
+ # mlx-community/Qwen2.5-VL-32B-Instruct-bf16
13
+ This model was converted to MLX format from [`Qwen/Qwen2.5-VL-32B-Instruct`]() using mlx-vlm version **0.1.21**.
14
+ Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct) for more details on the model.
15
+ ## Use with mlx
16
+
17
+ ```bash
18
+ pip install -U mlx-vlm
19
+ ```
20
+
21
+ ```bash
22
+ python -m mlx_vlm.generate --model mlx-community/Qwen2.5-VL-32B-Instruct-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
23
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
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 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "Qwen2_5_VLForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bad_words_ids": null,
9
+ "begin_suppress_tokens": null,
10
+ "bos_token_id": null,
11
+ "chunk_size_feed_forward": 0,
12
+ "cross_attention_hidden_size": null,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "encoder_no_repeat_ngram_size": 0,
18
+ "eos_token_id": 151645,
19
+ "exponential_decay_length_penalty": null,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "image_token_id": 151655,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 27648,
32
+ "is_decoder": false,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "max_position_embeddings": 128000,
41
+ "max_window_layers": 64,
42
+ "min_length": 0,
43
+ "model_type": "qwen2_5_vl",
44
+ "no_repeat_ngram_size": 0,
45
+ "num_attention_heads": 40,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_hidden_layers": 64,
49
+ "num_key_value_heads": 8,
50
+ "num_return_sequences": 1,
51
+ "output_attentions": false,
52
+ "output_hidden_states": false,
53
+ "output_scores": false,
54
+ "pad_token_id": 151643,
55
+ "prefix": null,
56
+ "problem_type": null,
57
+ "pruned_heads": {},
58
+ "remove_invalid_values": false,
59
+ "repetition_penalty": 1.0,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": {
64
+ "mrope_section": [
65
+ 16,
66
+ 24,
67
+ 24
68
+ ],
69
+ "rope_type": "default",
70
+ "type": "default"
71
+ },
72
+ "rope_theta": 1000000.0,
73
+ "sep_token_id": null,
74
+ "sliding_window": 32768,
75
+ "suppress_tokens": null,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": false,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": "bfloat16",
85
+ "torchscript": false,
86
+ "transformers_version": "4.50.0",
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "use_sliding_window": false,
91
+ "video_token_id": 151656,
92
+ "vision_config": {
93
+ "return_dict": true,
94
+ "output_hidden_states": false,
95
+ "output_attentions": false,
96
+ "torchscript": false,
97
+ "torch_dtype": "bfloat16",
98
+ "use_bfloat16": false,
99
+ "tf_legacy_loss": false,
100
+ "pruned_heads": {},
101
+ "tie_word_embeddings": true,
102
+ "chunk_size_feed_forward": 0,
103
+ "is_encoder_decoder": false,
104
+ "is_decoder": false,
105
+ "cross_attention_hidden_size": null,
106
+ "add_cross_attention": false,
107
+ "tie_encoder_decoder": false,
108
+ "max_length": 20,
109
+ "min_length": 0,
110
+ "do_sample": false,
111
+ "early_stopping": false,
112
+ "num_beams": 1,
113
+ "num_beam_groups": 1,
114
+ "diversity_penalty": 0.0,
115
+ "temperature": 1.0,
116
+ "top_k": 50,
117
+ "top_p": 1.0,
118
+ "typical_p": 1.0,
119
+ "repetition_penalty": 1.0,
120
+ "length_penalty": 1.0,
121
+ "no_repeat_ngram_size": 0,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "bad_words_ids": null,
124
+ "num_return_sequences": 1,
125
+ "output_scores": false,
126
+ "return_dict_in_generate": false,
127
+ "forced_bos_token_id": null,
128
+ "forced_eos_token_id": null,
129
+ "remove_invalid_values": false,
130
+ "exponential_decay_length_penalty": null,
131
+ "suppress_tokens": null,
132
+ "begin_suppress_tokens": null,
133
+ "architectures": null,
134
+ "finetuning_task": null,
135
+ "id2label": {
136
+ "0": "LABEL_0",
137
+ "1": "LABEL_1"
138
+ },
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "tokenizer_class": null,
144
+ "prefix": null,
145
+ "bos_token_id": null,
146
+ "pad_token_id": null,
147
+ "eos_token_id": null,
148
+ "sep_token_id": null,
149
+ "decoder_start_token_id": null,
150
+ "task_specific_params": null,
151
+ "problem_type": null,
152
+ "_name_or_path": "",
153
+ "_attn_implementation_autoset": false,
154
+ "in_chans": 3,
155
+ "model_type": "qwen2_5_vl",
156
+ "spatial_patch_size": 14,
157
+ "depth": 32,
158
+ "hidden_size": 1280,
159
+ "hidden_act": "silu",
160
+ "intermediate_size": 3456,
161
+ "num_heads": 16,
162
+ "in_channels": 3,
163
+ "patch_size": 14,
164
+ "spatial_merge_size": 2,
165
+ "temporal_patch_size": 2,
166
+ "tokens_per_second": 2,
167
+ "window_size": 112,
168
+ "fullatt_block_indexes": [
169
+ 7,
170
+ 15,
171
+ 23,
172
+ 31
173
+ ],
174
+ "out_hidden_size": 5120
175
+ },
176
+ "vision_end_token_id": 151653,
177
+ "vision_start_token_id": 151652,
178
+ "vision_token_id": 151654,
179
+ "vocab_size": 152064
180
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "pad_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.000001,
11
+ "transformers_version": "4.49.0"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5673561168f2889cbf653b827e60b6e9005782d867e8408f0d280098a53671
3
+ size 5294248269
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c3c4753a795462c2ef184ac53694f80134a4894fe6a61119b02e70a8ac6ff8
3
+ size 5159175906
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc23deeba055aab83ceb5106d901d11e73b726efc3179c160b6372086a2b8afc
3
+ size 5285041001
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e97cfd5cfde6387b3ab392a84e8cfd8d27ec83c3cd34d7e21fb03a6a6430de
3
+ size 5159175973
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c3da64fd95fd38823357f50d3bfa360b6469550a85f866bd4beb40d305e1dc
3
+ size 5159175963
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdec77b35e598905a9ed604401e4f3f50a5b9e5894b78f08b79d46a3d99b92af
3
+ size 5285041028
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a31fba5f141a2ef0a0f7331777fbf435f860716d78bb33c775847825b913255
3
+ size 5159175963
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1885e29fe537e8a1245deabef8ac8eafacd6f3953688e23c27499271d01c731d
3
+ size 5159175945
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b75cf77bc43c0315025f4f570ee9d8d63ce30e366c384c340f7396d2a9350a
3
+ size 5285041036
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa01ee7676e11ae9d7d2f036a092a188a50210cc65ec22a2c216beda9cb2196
3
+ size 5159175973
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13afdd89fb229f78ab98519f0b1949a008633fb0fc28221800464f2082d57d13
3
+ size 5159175977
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f1284a932393c8956d7c1134c8096b6335ca3fe1b353fb2e20ab1b907eaa2d
3
+ size 5285041056
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d653141cd1b2f3d4a087b13e5ca9dacd1bbb97e2ee403af25b43eb24a17652
3
+ size 4356937608
model.safetensors.index.json ADDED
@@ -0,0 +1,1168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 66905436672
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00018-of-00018.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00018.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00018.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00018.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00018.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00018.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00018.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00018.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00018.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00018.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00018.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00018.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00018.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00005-of-00018.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00018.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00018.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00018.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00005-of-00018.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00018.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00018.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00006-of-00018.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00018.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00018.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00018.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00006-of-00018.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00006-of-00018.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00018.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00006-of-00018.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00007-of-00018.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00018.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00018.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00018.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00007-of-00018.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00007-of-00018.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00007-of-00018.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00008-of-00018.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00018.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00018.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00018.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00008-of-00018.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00008-of-00018.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00008-of-00018.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00009-of-00018.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00018.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00018.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00018.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00018.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00009-of-00018.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00009-of-00018.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00009-of-00018.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00010-of-00018.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00018.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00018.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00018.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00010-of-00018.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00010-of-00018.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00010-of-00018.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00011-of-00018.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00010-of-00018.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00010-of-00018.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00010-of-00018.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00011-of-00018.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00011-of-00018.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00018.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00011-of-00018.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00012-of-00018.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00011-of-00018.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00011-of-00018.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00011-of-00018.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00012-of-00018.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00012-of-00018.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00012-of-00018.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00013-of-00018.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00012-of-00018.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00012-of-00018.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00012-of-00018.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00013-of-00018.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00013-of-00018.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00013-of-00018.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00014-of-00018.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00013-of-00018.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00013-of-00018.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00013-of-00018.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00018.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00018.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00018.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00018.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00014-of-00018.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00014-of-00018.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00014-of-00018.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00015-of-00018.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00014-of-00018.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00014-of-00018.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00014-of-00018.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00015-of-00018.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00015-of-00018.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00015-of-00018.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00016-of-00018.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00015-of-00018.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00015-of-00018.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00018.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00016-of-00018.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00016-of-00018.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00018.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00016-of-00018.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00017-of-00018.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00016-of-00018.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00016-of-00018.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00016-of-00018.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00017-of-00018.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00017-of-00018.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00017-of-00018.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00017-of-00018.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00017-of-00018.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00018.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00018.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00018.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00018.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00018.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00018.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
776
+ "model.norm.weight": "model-00017-of-00018.safetensors",
777
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00018.safetensors",
778
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00018.safetensors",
779
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00018.safetensors",
780
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00018.safetensors",
781
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
782
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
783
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
784
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
785
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
786
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
787
+ "visual.blocks.0.norm1.weight": "model-00001-of-00018.safetensors",
788
+ "visual.blocks.0.norm2.weight": "model-00001-of-00018.safetensors",
789
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00018.safetensors",
790
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00018.safetensors",
791
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00018.safetensors",
792
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00018.safetensors",
793
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
794
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
795
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
796
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
797
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
798
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
799
+ "visual.blocks.1.norm1.weight": "model-00001-of-00018.safetensors",
800
+ "visual.blocks.1.norm2.weight": "model-00001-of-00018.safetensors",
801
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00018.safetensors",
802
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00018.safetensors",
803
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00018.safetensors",
804
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00018.safetensors",
805
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
806
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
807
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
808
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
809
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
810
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
811
+ "visual.blocks.10.norm1.weight": "model-00001-of-00018.safetensors",
812
+ "visual.blocks.10.norm2.weight": "model-00001-of-00018.safetensors",
813
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00018.safetensors",
814
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00018.safetensors",
815
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00018.safetensors",
816
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00018.safetensors",
817
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
818
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
819
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
820
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
821
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
822
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
823
+ "visual.blocks.11.norm1.weight": "model-00001-of-00018.safetensors",
824
+ "visual.blocks.11.norm2.weight": "model-00001-of-00018.safetensors",
825
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00018.safetensors",
826
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00018.safetensors",
827
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00018.safetensors",
828
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00018.safetensors",
829
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
830
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
831
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
832
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
833
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
834
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
835
+ "visual.blocks.12.norm1.weight": "model-00001-of-00018.safetensors",
836
+ "visual.blocks.12.norm2.weight": "model-00001-of-00018.safetensors",
837
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00018.safetensors",
838
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00018.safetensors",
839
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00018.safetensors",
840
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00018.safetensors",
841
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
842
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
843
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
844
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
845
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
846
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
847
+ "visual.blocks.13.norm1.weight": "model-00001-of-00018.safetensors",
848
+ "visual.blocks.13.norm2.weight": "model-00001-of-00018.safetensors",
849
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00018.safetensors",
850
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00018.safetensors",
851
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00018.safetensors",
852
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00018.safetensors",
853
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
854
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
855
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
856
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
857
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
858
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
859
+ "visual.blocks.14.norm1.weight": "model-00001-of-00018.safetensors",
860
+ "visual.blocks.14.norm2.weight": "model-00001-of-00018.safetensors",
861
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00018.safetensors",
862
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00018.safetensors",
863
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00018.safetensors",
864
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00018.safetensors",
865
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
866
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
867
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
868
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
869
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
870
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
871
+ "visual.blocks.15.norm1.weight": "model-00001-of-00018.safetensors",
872
+ "visual.blocks.15.norm2.weight": "model-00001-of-00018.safetensors",
873
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00018.safetensors",
874
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00018.safetensors",
875
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00018.safetensors",
876
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00018.safetensors",
877
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
878
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
879
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
880
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
881
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
882
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
883
+ "visual.blocks.16.norm1.weight": "model-00001-of-00018.safetensors",
884
+ "visual.blocks.16.norm2.weight": "model-00001-of-00018.safetensors",
885
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00018.safetensors",
886
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00018.safetensors",
887
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00018.safetensors",
888
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00018.safetensors",
889
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
890
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
891
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
892
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
893
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
894
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
895
+ "visual.blocks.17.norm1.weight": "model-00001-of-00018.safetensors",
896
+ "visual.blocks.17.norm2.weight": "model-00001-of-00018.safetensors",
897
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00018.safetensors",
898
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00018.safetensors",
899
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00018.safetensors",
900
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00018.safetensors",
901
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
902
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
903
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
904
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
905
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
906
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
907
+ "visual.blocks.18.norm1.weight": "model-00001-of-00018.safetensors",
908
+ "visual.blocks.18.norm2.weight": "model-00001-of-00018.safetensors",
909
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00018.safetensors",
910
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00018.safetensors",
911
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00018.safetensors",
912
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00018.safetensors",
913
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
914
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
915
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
916
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
917
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
918
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
919
+ "visual.blocks.19.norm1.weight": "model-00001-of-00018.safetensors",
920
+ "visual.blocks.19.norm2.weight": "model-00001-of-00018.safetensors",
921
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00018.safetensors",
922
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00018.safetensors",
923
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00018.safetensors",
924
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00018.safetensors",
925
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
926
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
927
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
928
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
929
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
930
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
931
+ "visual.blocks.2.norm1.weight": "model-00001-of-00018.safetensors",
932
+ "visual.blocks.2.norm2.weight": "model-00001-of-00018.safetensors",
933
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00018.safetensors",
934
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00018.safetensors",
935
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00018.safetensors",
936
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00018.safetensors",
937
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
938
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
939
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
940
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
941
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
942
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
943
+ "visual.blocks.20.norm1.weight": "model-00001-of-00018.safetensors",
944
+ "visual.blocks.20.norm2.weight": "model-00001-of-00018.safetensors",
945
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00018.safetensors",
946
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00018.safetensors",
947
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00018.safetensors",
948
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00018.safetensors",
949
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
950
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
951
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
952
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
953
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
954
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
955
+ "visual.blocks.21.norm1.weight": "model-00001-of-00018.safetensors",
956
+ "visual.blocks.21.norm2.weight": "model-00001-of-00018.safetensors",
957
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00018.safetensors",
958
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00018.safetensors",
959
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00018.safetensors",
960
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00018.safetensors",
961
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
962
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
963
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
964
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
965
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
966
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
967
+ "visual.blocks.22.norm1.weight": "model-00001-of-00018.safetensors",
968
+ "visual.blocks.22.norm2.weight": "model-00001-of-00018.safetensors",
969
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00018.safetensors",
970
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00018.safetensors",
971
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00018.safetensors",
972
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00018.safetensors",
973
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
974
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
975
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
976
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
977
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
978
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
979
+ "visual.blocks.23.norm1.weight": "model-00001-of-00018.safetensors",
980
+ "visual.blocks.23.norm2.weight": "model-00001-of-00018.safetensors",
981
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00018.safetensors",
982
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00018.safetensors",
983
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00018.safetensors",
984
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00018.safetensors",
985
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
986
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
987
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
988
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
989
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
990
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
991
+ "visual.blocks.24.norm1.weight": "model-00001-of-00018.safetensors",
992
+ "visual.blocks.24.norm2.weight": "model-00001-of-00018.safetensors",
993
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00018.safetensors",
994
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00018.safetensors",
995
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00018.safetensors",
996
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00018.safetensors",
997
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
998
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
999
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1000
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1001
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1002
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1003
+ "visual.blocks.25.norm1.weight": "model-00001-of-00018.safetensors",
1004
+ "visual.blocks.25.norm2.weight": "model-00001-of-00018.safetensors",
1005
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00018.safetensors",
1006
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00018.safetensors",
1007
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00018.safetensors",
1008
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00018.safetensors",
1009
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1010
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1011
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1012
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1013
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1014
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1015
+ "visual.blocks.26.norm1.weight": "model-00001-of-00018.safetensors",
1016
+ "visual.blocks.26.norm2.weight": "model-00001-of-00018.safetensors",
1017
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00018.safetensors",
1018
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00018.safetensors",
1019
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00018.safetensors",
1020
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00018.safetensors",
1021
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1022
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1023
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1024
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1025
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1026
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1027
+ "visual.blocks.27.norm1.weight": "model-00001-of-00018.safetensors",
1028
+ "visual.blocks.27.norm2.weight": "model-00001-of-00018.safetensors",
1029
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00018.safetensors",
1030
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00018.safetensors",
1031
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00018.safetensors",
1032
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00018.safetensors",
1033
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1034
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1035
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1036
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1037
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1038
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1039
+ "visual.blocks.28.norm1.weight": "model-00001-of-00018.safetensors",
1040
+ "visual.blocks.28.norm2.weight": "model-00001-of-00018.safetensors",
1041
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00018.safetensors",
1042
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00018.safetensors",
1043
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00018.safetensors",
1044
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00018.safetensors",
1045
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1046
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1047
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1048
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1049
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1050
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1051
+ "visual.blocks.29.norm1.weight": "model-00001-of-00018.safetensors",
1052
+ "visual.blocks.29.norm2.weight": "model-00001-of-00018.safetensors",
1053
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00018.safetensors",
1054
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00018.safetensors",
1055
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00018.safetensors",
1056
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00018.safetensors",
1057
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1058
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1059
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1060
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1061
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1062
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1063
+ "visual.blocks.3.norm1.weight": "model-00001-of-00018.safetensors",
1064
+ "visual.blocks.3.norm2.weight": "model-00001-of-00018.safetensors",
1065
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00018.safetensors",
1066
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00018.safetensors",
1067
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00018.safetensors",
1068
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00018.safetensors",
1069
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1070
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1071
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1072
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1073
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1074
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1075
+ "visual.blocks.30.norm1.weight": "model-00001-of-00018.safetensors",
1076
+ "visual.blocks.30.norm2.weight": "model-00001-of-00018.safetensors",
1077
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00018.safetensors",
1078
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00018.safetensors",
1079
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00018.safetensors",
1080
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00018.safetensors",
1081
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1082
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1083
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1084
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1085
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1086
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1087
+ "visual.blocks.31.norm1.weight": "model-00001-of-00018.safetensors",
1088
+ "visual.blocks.31.norm2.weight": "model-00001-of-00018.safetensors",
1089
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00018.safetensors",
1090
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00018.safetensors",
1091
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00018.safetensors",
1092
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00018.safetensors",
1093
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1094
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1095
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1096
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1097
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1098
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1099
+ "visual.blocks.4.norm1.weight": "model-00001-of-00018.safetensors",
1100
+ "visual.blocks.4.norm2.weight": "model-00001-of-00018.safetensors",
1101
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00018.safetensors",
1102
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00018.safetensors",
1103
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00018.safetensors",
1104
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00018.safetensors",
1105
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1106
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1107
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1108
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1109
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1110
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1111
+ "visual.blocks.5.norm1.weight": "model-00001-of-00018.safetensors",
1112
+ "visual.blocks.5.norm2.weight": "model-00001-of-00018.safetensors",
1113
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00018.safetensors",
1114
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00018.safetensors",
1115
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00018.safetensors",
1116
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00018.safetensors",
1117
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1118
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1119
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1120
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1121
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1122
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1123
+ "visual.blocks.6.norm1.weight": "model-00001-of-00018.safetensors",
1124
+ "visual.blocks.6.norm2.weight": "model-00001-of-00018.safetensors",
1125
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00018.safetensors",
1126
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00018.safetensors",
1127
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00018.safetensors",
1128
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00018.safetensors",
1129
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1130
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1131
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1132
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1133
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1134
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1135
+ "visual.blocks.7.norm1.weight": "model-00001-of-00018.safetensors",
1136
+ "visual.blocks.7.norm2.weight": "model-00001-of-00018.safetensors",
1137
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00018.safetensors",
1138
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00018.safetensors",
1139
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00018.safetensors",
1140
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00018.safetensors",
1141
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1142
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1143
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1144
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1145
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1146
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1147
+ "visual.blocks.8.norm1.weight": "model-00001-of-00018.safetensors",
1148
+ "visual.blocks.8.norm2.weight": "model-00001-of-00018.safetensors",
1149
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00018.safetensors",
1150
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00018.safetensors",
1151
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00018.safetensors",
1152
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00018.safetensors",
1153
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00018.safetensors",
1154
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00018.safetensors",
1155
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00018.safetensors",
1156
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00018.safetensors",
1157
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00018.safetensors",
1158
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00018.safetensors",
1159
+ "visual.blocks.9.norm1.weight": "model-00001-of-00018.safetensors",
1160
+ "visual.blocks.9.norm2.weight": "model-00001-of-00018.safetensors",
1161
+ "visual.merger.ln_q.weight": "model-00001-of-00018.safetensors",
1162
+ "visual.merger.mlp.0.bias": "model-00001-of-00018.safetensors",
1163
+ "visual.merger.mlp.0.weight": "model-00001-of-00018.safetensors",
1164
+ "visual.merger.mlp.2.bias": "model-00001-of-00018.safetensors",
1165
+ "visual.merger.mlp.2.weight": "model-00001-of-00018.safetensors",
1166
+ "visual.patch_embed.proj.weight": "model-00001-of-00018.safetensors"
1167
+ }
1168
+ }
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": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff