coolAI commited on
Commit
452ce81
·
verified ·
1 Parent(s): 44151b7

(Trained with Unsloth)

Browse files
Files changed (2) hide show
  1. config.json +137 -0
  2. tokenizer_config.json +3 -2
config.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 3584,
9
+ "image_token_id": 151655,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2_5_vl",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 151654,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "architectures": [
33
+ "Qwen2_5_VLForConditionalGeneration"
34
+ ],
35
+ "attention_dropout": 0.0,
36
+ "bos_token_id": 151643,
37
+ "eos_token_id": 151645,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 3584,
40
+ "image_token_id": null,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 18944,
43
+ "layer_types": [
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention"
72
+ ],
73
+ "max_position_embeddings": 128000,
74
+ "max_window_layers": 28,
75
+ "model_type": "qwen2_5_vl_text",
76
+ "num_attention_heads": 28,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 4,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": {
81
+ "mrope_section": [
82
+ 16,
83
+ 24,
84
+ 24
85
+ ],
86
+ "rope_type": "default",
87
+ "type": "default"
88
+ },
89
+ "rope_theta": 1000000.0,
90
+ "sliding_window": null,
91
+ "torch_dtype": "bfloat16",
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "video_token_id": null,
95
+ "vision_end_token_id": 151653,
96
+ "vision_start_token_id": 151652,
97
+ "vision_token_id": 151654,
98
+ "vocab_size": 152064
99
+ },
100
+ "tie_word_embeddings": false,
101
+ "torch_dtype": "bfloat16",
102
+ "transformers_version": "4.55.4",
103
+ "unsloth_fixed": true,
104
+ "unsloth_version": "2025.10.1",
105
+ "use_cache": true,
106
+ "use_sliding_window": false,
107
+ "video_token_id": 151656,
108
+ "vision_config": {
109
+ "depth": 32,
110
+ "fullatt_block_indexes": [
111
+ 7,
112
+ 15,
113
+ 23,
114
+ 31
115
+ ],
116
+ "hidden_act": "silu",
117
+ "hidden_size": 1280,
118
+ "in_channels": 3,
119
+ "in_chans": 3,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3420,
122
+ "model_type": "qwen2_5_vl",
123
+ "num_heads": 16,
124
+ "out_hidden_size": 3584,
125
+ "patch_size": 14,
126
+ "spatial_merge_size": 2,
127
+ "spatial_patch_size": 14,
128
+ "temporal_patch_size": 2,
129
+ "tokens_per_second": 2,
130
+ "torch_dtype": "bfloat16",
131
+ "window_size": 112
132
+ },
133
+ "vision_end_token_id": 151653,
134
+ "vision_start_token_id": 151652,
135
+ "vision_token_id": 151654,
136
+ "vocab_size": 152064
137
+ }
tokenizer_config.json CHANGED
@@ -205,5 +205,6 @@
205
  "processor_class": "Qwen2_5_VLProcessor",
206
  "split_special_tokens": false,
207
  "tokenizer_class": "Qwen2Tokenizer",
208
- "unk_token": null
209
- }
 
 
205
  "processor_class": "Qwen2_5_VLProcessor",
206
  "split_special_tokens": false,
207
  "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null,
209
+ "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 %}"
210
+ }