Hugging Face's logo

unsloth
/
Qwen3.5-2B

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
unsloth
conversational
Model card Files
xet
 Community
2
danielhanchen commited on
Commit
60296b0
·
verified ·
1 Parent(s): 3c7f026

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. added_tokens.json +35 -0
  2. config.json +11 -14
  3. merges.txt +1 -0
  4. preprocessor_config.json +26 -8
  5. special_tokens_map.json +38 -0
  6. tokenizer_config.json +286 -6
  7. video_preprocessor_config.json +40 -20
  8. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 248069,
3
+ "</tool_call>": 248059,
4
+ "</tool_response>": 248067,
5
+ "<think>": 248068,
6
+ "<tool_call>": 248058,
7
+ "<tool_response>": 248066,
8
+ "<tts_pad>": 248072,
9
+ "<tts_text_bos>": 248073,
10
+ "<tts_text_bos_single>": 248075,
11
+ "<tts_text_eod>": 248074,
12
+ "<|audio_end|>": 248071,
13
+ "<|audio_pad|>": 248076,
14
+ "<|audio_start|>": 248070,
15
+ "<|box_end|>": 248050,
16
+ "<|box_start|>": 248049,
17
+ "<|endoftext|>": 248044,
18
+ "<|file_sep|>": 248065,
19
+ "<|fim_middle|>": 248061,
20
+ "<|fim_pad|>": 248063,
21
+ "<|fim_prefix|>": 248060,
22
+ "<|fim_suffix|>": 248062,
23
+ "<|im_end|>": 248046,
24
+ "<|im_start|>": 248045,
25
+ "<|image_pad|>": 248056,
26
+ "<|object_ref_end|>": 248048,
27
+ "<|object_ref_start|>": 248047,
28
+ "<|quad_end|>": 248052,
29
+ "<|quad_start|>": 248051,
30
+ "<|repo_name|>": 248064,
31
+ "<|video_pad|>": 248057,
32
+ "<|vision_end|>": 248054,
33
+ "<|vision_pad|>": 248055,
34
+ "<|vision_start|>": 248053
35
+ }
config.json CHANGED
@@ -4,12 +4,10 @@
4
  ],
5
  "image_token_id": 248056,
6
  "model_type": "qwen3_5",
7
- "pad_token_id": 248055,
8
  "text_config": {
9
  "attention_bias": false,
10
  "attention_dropout": 0.0,
11
  "attn_output_gate": true,
12
- "bos_token_id": null,
13
  "torch_dtype": "bfloat16",
14
  "eos_token_id": 248044,
15
  "full_attention_interval": 4,
@@ -49,7 +47,6 @@
49
  "linear_num_key_heads": 16,
50
  "linear_num_value_heads": 16,
51
  "linear_value_head_dim": 128,
52
- "mamba_ssm_dtype": "float32",
53
  "max_position_embeddings": 262144,
54
  "mlp_only_layers": [],
55
  "model_type": "qwen3_5_text",
@@ -58,9 +55,11 @@
58
  "num_attention_heads": 8,
59
  "num_hidden_layers": 24,
60
  "num_key_value_heads": 2,
61
- "pad_token_id": null,
62
- "partial_rotary_factor": 0.25,
63
  "rms_norm_eps": 1e-06,
 
 
 
 
64
  "rope_parameters": {
65
  "mrope_interleaved": true,
66
  "mrope_section": [
@@ -68,17 +67,13 @@
68
  11,
69
  10
70
  ],
71
- "partial_rotary_factor": 0.25,
72
  "rope_theta": 10000000,
73
- "rope_type": "default"
74
- },
75
- "tie_word_embeddings": true,
76
- "use_cache": true,
77
- "vocab_size": 248320
78
  },
79
  "tie_word_embeddings": true,
80
- "transformers_version": "5.3.0.dev0",
81
- "unsloth_fixed": true,
82
  "video_token_id": 248057,
83
  "vision_config": {
84
  "deepstack_visual_indexes": [],
@@ -97,5 +92,7 @@
97
  "temporal_patch_size": 2
98
  },
99
  "vision_end_token_id": 248054,
100
- "vision_start_token_id": 248053
 
 
101
  }
 
4
  ],
5
  "image_token_id": 248056,
6
  "model_type": "qwen3_5",
 
7
  "text_config": {
8
  "attention_bias": false,
9
  "attention_dropout": 0.0,
10
  "attn_output_gate": true,
 
11
  "torch_dtype": "bfloat16",
12
  "eos_token_id": 248044,
13
  "full_attention_interval": 4,
 
47
  "linear_num_key_heads": 16,
48
  "linear_num_value_heads": 16,
49
  "linear_value_head_dim": 128,
 
50
  "max_position_embeddings": 262144,
51
  "mlp_only_layers": [],
52
  "model_type": "qwen3_5_text",
 
55
  "num_attention_heads": 8,
56
  "num_hidden_layers": 24,
57
  "num_key_value_heads": 2,
 
 
58
  "rms_norm_eps": 1e-06,
59
+ "tie_word_embeddings": true,
60
+ "use_cache": true,
61
+ "vocab_size": 248320,
62
+ "mamba_ssm_dtype": "float32",
63
  "rope_parameters": {
64
  "mrope_interleaved": true,
65
  "mrope_section": [
 
67
  11,
68
  10
69
  ],
70
+ "rope_type": "default",
71
  "rope_theta": 10000000,
72
+ "partial_rotary_factor": 0.25
73
+ }
 
 
 
74
  },
75
  "tie_word_embeddings": true,
76
+ "transformers_version": "4.57.0.dev0",
 
77
  "video_token_id": 248057,
78
  "vision_config": {
79
  "deepstack_visual_indexes": [],
 
92
  "temporal_patch_size": 2
93
  },
94
  "vision_end_token_id": 248054,
95
+ "vision_start_token_id": 248053,
96
+ "mtp_num_hidden_layers": 1,
97
+ "unsloth_fixed_mtp": true
98
  }
merges.txt CHANGED
@@ -1,3 +1,4 @@
 
1
  Ġ Ġ
2
  ĠĠ ĠĠ
3
  i n
 
1
+ #version: 0.2
2
  Ġ Ġ
3
  ĠĠ ĠĠ
4
  i n
preprocessor_config.json CHANGED
@@ -1,21 +1,39 @@
1
  {
2
- "size": {
3
- "longest_edge": 16777216,
4
- "shortest_edge": 65536
5
- },
6
- "patch_size": 16,
7
- "temporal_patch_size": 2,
8
- "merge_size": 2,
 
 
 
 
9
  "image_mean": [
10
  0.5,
11
  0.5,
12
  0.5
13
  ],
 
14
  "image_std": [
15
  0.5,
16
  0.5,
17
  0.5
18
  ],
 
 
 
 
 
 
19
  "processor_class": "Qwen3VLProcessor",
20
- "image_processor_type": "Qwen2VLImageProcessorFast"
 
 
 
 
 
 
 
21
  }
 
1
  {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
  "image_mean": [
14
  0.5,
15
  0.5,
16
  0.5
17
  ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
  "image_std": [
20
  0.5,
21
  0.5,
22
  0.5
23
  ],
24
+ "input_data_format": null,
25
+ "max_pixels": null,
26
+ "merge_size": 2,
27
+ "min_pixels": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
  "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 16777216,
36
+ "shortest_edge": 65536
37
+ },
38
+ "temporal_patch_size": 2
39
  }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "audio_bos_token": "<|audio_start|>",
18
+ "audio_eos_token": "<|audio_end|>",
19
+ "audio_token": "<|audio_pad|>",
20
+ "eos_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<|image_pad|>",
28
+ "pad_token": {
29
+ "content": "<|vision_pad|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "video_token": "<|video_pad|>",
36
+ "vision_bos_token": "<|vision_start|>",
37
+ "vision_eos_token": "<|vision_end|>"
38
+ }
tokenizer_config.json CHANGED
@@ -1,17 +1,295 @@
1
  {
 
2
  "add_prefix_space": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "audio_bos_token": "<|audio_start|>",
4
  "audio_eos_token": "<|audio_end|>",
5
  "audio_token": "<|audio_pad|>",
6
- "backend": "tokenizers",
7
  "bos_token": null,
8
  "clean_up_tokenization_spaces": false,
9
  "eos_token": "<|im_end|>",
10
  "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": true,
13
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
  "audio_bos_token": "<|audio_start|>",
16
  "audio_eos_token": "<|audio_end|>",
17
  "audio_token": "<|audio_pad|>",
@@ -20,12 +298,14 @@
20
  "vision_bos_token": "<|vision_start|>",
21
  "vision_eos_token": "<|vision_end|>"
22
  },
 
 
23
  "pad_token": "<|vision_pad|>",
24
  "padding_side": "left",
25
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
  "processor_class": "Qwen3VLProcessor",
27
  "split_special_tokens": false,
28
- "tokenizer_class": "TokenizersBackend",
29
  "unk_token": null,
30
  "video_token": "<|video_pad|>",
31
  "vision_bos_token": "<|vision_start|>",
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "248044": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "248045": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "248046": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "248047": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "248048": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "248049": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "248050": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "248051": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "248052": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "248053": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "248054": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "248055": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "248056": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "248057": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "248058": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "248059": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "248060": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "248061": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "248062": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "248063": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "248064": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "248065": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "248066": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "248067": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "248068": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "248069": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "248070": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "248071": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "248072": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "248073": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "248074": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "248075": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "248076": {
262
+ "content": "<|audio_pad|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ }
269
+ },
270
+ "additional_special_tokens": [
271
+ "<|im_start|>",
272
+ "<|im_end|>",
273
+ "<|object_ref_start|>",
274
+ "<|object_ref_end|>",
275
+ "<|box_start|>",
276
+ "<|box_end|>",
277
+ "<|quad_start|>",
278
+ "<|quad_end|>",
279
+ "<|vision_start|>",
280
+ "<|vision_end|>",
281
+ "<|vision_pad|>",
282
+ "<|image_pad|>",
283
+ "<|video_pad|>"
284
+ ],
285
  "audio_bos_token": "<|audio_start|>",
286
  "audio_eos_token": "<|audio_end|>",
287
  "audio_token": "<|audio_pad|>",
 
288
  "bos_token": null,
289
  "clean_up_tokenization_spaces": false,
290
  "eos_token": "<|im_end|>",
291
  "errors": "replace",
292
+ "extra_special_tokens": {
 
 
 
293
  "audio_bos_token": "<|audio_start|>",
294
  "audio_eos_token": "<|audio_end|>",
295
  "audio_token": "<|audio_pad|>",
 
298
  "vision_bos_token": "<|vision_start|>",
299
  "vision_eos_token": "<|vision_end|>"
300
  },
301
+ "image_token": "<|image_pad|>",
302
+ "model_max_length": 262144,
303
  "pad_token": "<|vision_pad|>",
304
  "padding_side": "left",
305
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
306
  "processor_class": "Qwen3VLProcessor",
307
  "split_special_tokens": false,
308
+ "tokenizer_class": "Qwen2Tokenizer",
309
  "unk_token": null,
310
  "video_token": "<|video_pad|>",
311
  "vision_bos_token": "<|vision_start|>",
video_preprocessor_config.json CHANGED
@@ -1,21 +1,41 @@
1
  {
2
- "size": {
3
- "longest_edge": 25165824,
4
- "shortest_edge": 4096
5
- },
6
- "patch_size": 16,
7
- "temporal_patch_size": 2,
8
- "merge_size": 2,
9
- "image_mean": [
10
- 0.5,
11
- 0.5,
12
- 0.5
13
- ],
14
- "image_std": [
15
- 0.5,
16
- 0.5,
17
- 0.5
18
- ],
19
- "processor_class": "Qwen3VLProcessor",
20
- "video_processor_type": "Qwen3VLVideoProcessor"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff