trailio commited on
Commit
9db0fdf
·
verified ·
1 Parent(s): ae830cc

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "language_model_only": false,
8
+ "model_type": "qwen3_5",
9
+ "quantization_config": {
10
+ "_load_in_4bit": true,
11
+ "_load_in_8bit": false,
12
+ "bnb_4bit_compute_dtype": "bfloat16",
13
+ "bnb_4bit_quant_storage": "uint8",
14
+ "bnb_4bit_quant_type": "nf4",
15
+ "bnb_4bit_use_double_quant": true,
16
+ "llm_int8_enable_fp32_cpu_offload": false,
17
+ "llm_int8_has_fp16_weight": false,
18
+ "llm_int8_skip_modules": null,
19
+ "llm_int8_threshold": 6.0,
20
+ "load_in_4bit": true,
21
+ "load_in_8bit": false,
22
+ "quant_method": "bitsandbytes"
23
+ },
24
+ "text_config": {
25
+ "attention_bias": false,
26
+ "attention_dropout": 0.0,
27
+ "attn_output_gate": true,
28
+ "bos_token_id": 248044,
29
+ "dtype": "bfloat16",
30
+ "eos_token_id": 248044,
31
+ "full_attention_interval": 4,
32
+ "head_dim": 256,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 5120,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 17408,
37
+ "layer_types": [
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "full_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "full_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "full_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "full_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "full_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "full_attention",
90
+ "linear_attention",
91
+ "linear_attention",
92
+ "linear_attention",
93
+ "full_attention",
94
+ "linear_attention",
95
+ "linear_attention",
96
+ "linear_attention",
97
+ "full_attention",
98
+ "linear_attention",
99
+ "linear_attention",
100
+ "linear_attention",
101
+ "full_attention"
102
+ ],
103
+ "linear_conv_kernel_dim": 4,
104
+ "linear_key_head_dim": 128,
105
+ "linear_num_key_heads": 16,
106
+ "linear_num_value_heads": 48,
107
+ "linear_value_head_dim": 128,
108
+ "mamba_ssm_dtype": "float32",
109
+ "max_position_embeddings": 262144,
110
+ "model_type": "qwen3_5_text",
111
+ "mtp_num_hidden_layers": 1,
112
+ "mtp_use_dedicated_embeddings": false,
113
+ "num_attention_heads": 24,
114
+ "num_hidden_layers": 64,
115
+ "num_key_value_heads": 4,
116
+ "output_gate_type": "swish",
117
+ "pad_token_id": null,
118
+ "partial_rotary_factor": 0.25,
119
+ "rms_norm_eps": 1e-06,
120
+ "rope_parameters": {
121
+ "mrope_interleaved": true,
122
+ "mrope_section": [
123
+ 11,
124
+ 11,
125
+ 10
126
+ ],
127
+ "partial_rotary_factor": 0.25,
128
+ "rope_theta": 10000000,
129
+ "rope_type": "default"
130
+ },
131
+ "tie_word_embeddings": false,
132
+ "use_cache": true,
133
+ "vocab_size": 248320
134
+ },
135
+ "tie_word_embeddings": false,
136
+ "transformers_version": "5.5.0",
137
+ "video_token_id": 248057,
138
+ "vision_config": {
139
+ "deepstack_visual_indexes": [],
140
+ "depth": 27,
141
+ "dtype": "bfloat16",
142
+ "hidden_act": "gelu_pytorch_tanh",
143
+ "hidden_size": 1152,
144
+ "in_channels": 3,
145
+ "initializer_range": 0.02,
146
+ "intermediate_size": 4304,
147
+ "model_type": "qwen3_5",
148
+ "num_heads": 16,
149
+ "num_position_embeddings": 2304,
150
+ "out_hidden_size": 5120,
151
+ "patch_size": 16,
152
+ "spatial_merge_size": 2,
153
+ "temporal_patch_size": 2
154
+ },
155
+ "vision_end_token_id": 248054,
156
+ "vision_start_token_id": 248053
157
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.5.0"
13
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54d83c1d36631de231876217a8e0c2483eccee8746369a482b79442bdfc5d958
3
+ size 2542796928
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d889e7646f9dd53e8fe62ca9357a765f694acc448dd7d459ee3499db8422d90
3
+ size 4959186781
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766e6a5cf16e1a9da627636f811217a4f4a0e7b0527dd14c3474e4d2ce65878d
3
+ size 4956854549
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ab41fe0fc16a1060654163464a738f484b8125bdfec98fdced1c0fce7e908f
3
+ size 4956854533
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135033007e56826822b6fd7abf8f53822a0311ff9633565010c0039f5b7cb9b4
3
+ size 483173359
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
tokenizer_config.json CHANGED
@@ -21,278 +21,12 @@
21
  "vision_eos_token": "<|vision_end|>"
22
  },
23
  "pad_token": "<|endoftext|>",
24
- "padding_side": "right",
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
  "split_special_tokens": false,
27
  "tokenizer_class": "TokenizersBackend",
28
  "unk_token": null,
29
  "video_token": "<|video_pad|>",
30
  "vision_bos_token": "<|vision_start|>",
31
- "vision_eos_token": "<|vision_end|>",
32
- "added_tokens_decoder": {
33
- "248044": {
34
- "content": "<|endoftext|>",
35
- "single_word": false,
36
- "lstrip": false,
37
- "rstrip": false,
38
- "normalized": false,
39
- "special": true
40
- },
41
- "248045": {
42
- "content": "<|im_start|>",
43
- "single_word": false,
44
- "lstrip": false,
45
- "rstrip": false,
46
- "normalized": false,
47
- "special": true
48
- },
49
- "248046": {
50
- "content": "<|im_end|>",
51
- "single_word": false,
52
- "lstrip": false,
53
- "rstrip": false,
54
- "normalized": false,
55
- "special": true
56
- },
57
- "248047": {
58
- "content": "<|object_ref_start|>",
59
- "single_word": false,
60
- "lstrip": false,
61
- "rstrip": false,
62
- "normalized": false,
63
- "special": true
64
- },
65
- "248048": {
66
- "content": "<|object_ref_end|>",
67
- "single_word": false,
68
- "lstrip": false,
69
- "rstrip": false,
70
- "normalized": false,
71
- "special": true
72
- },
73
- "248049": {
74
- "content": "<|box_start|>",
75
- "single_word": false,
76
- "lstrip": false,
77
- "rstrip": false,
78
- "normalized": false,
79
- "special": true
80
- },
81
- "248050": {
82
- "content": "<|box_end|>",
83
- "single_word": false,
84
- "lstrip": false,
85
- "rstrip": false,
86
- "normalized": false,
87
- "special": true
88
- },
89
- "248051": {
90
- "content": "<|quad_start|>",
91
- "single_word": false,
92
- "lstrip": false,
93
- "rstrip": false,
94
- "normalized": false,
95
- "special": true
96
- },
97
- "248052": {
98
- "content": "<|quad_end|>",
99
- "single_word": false,
100
- "lstrip": false,
101
- "rstrip": false,
102
- "normalized": false,
103
- "special": true
104
- },
105
- "248053": {
106
- "content": "<|vision_start|>",
107
- "single_word": false,
108
- "lstrip": false,
109
- "rstrip": false,
110
- "normalized": false,
111
- "special": true
112
- },
113
- "248054": {
114
- "content": "<|vision_end|>",
115
- "single_word": false,
116
- "lstrip": false,
117
- "rstrip": false,
118
- "normalized": false,
119
- "special": true
120
- },
121
- "248055": {
122
- "content": "<|vision_pad|>",
123
- "single_word": false,
124
- "lstrip": false,
125
- "rstrip": false,
126
- "normalized": false,
127
- "special": true
128
- },
129
- "248056": {
130
- "content": "<|image_pad|>",
131
- "single_word": false,
132
- "lstrip": false,
133
- "rstrip": false,
134
- "normalized": false,
135
- "special": true
136
- },
137
- "248057": {
138
- "content": "<|video_pad|>",
139
- "single_word": false,
140
- "lstrip": false,
141
- "rstrip": false,
142
- "normalized": false,
143
- "special": true
144
- },
145
- "248058": {
146
- "content": "<tool_call>",
147
- "single_word": false,
148
- "lstrip": false,
149
- "rstrip": false,
150
- "normalized": false,
151
- "special": false
152
- },
153
- "248059": {
154
- "content": "</tool_call>",
155
- "single_word": false,
156
- "lstrip": false,
157
- "rstrip": false,
158
- "normalized": false,
159
- "special": false
160
- },
161
- "248060": {
162
- "content": "<|fim_prefix|>",
163
- "single_word": false,
164
- "lstrip": false,
165
- "rstrip": false,
166
- "normalized": false,
167
- "special": false
168
- },
169
- "248061": {
170
- "content": "<|fim_middle|>",
171
- "single_word": false,
172
- "lstrip": false,
173
- "rstrip": false,
174
- "normalized": false,
175
- "special": false
176
- },
177
- "248062": {
178
- "content": "<|fim_suffix|>",
179
- "single_word": false,
180
- "lstrip": false,
181
- "rstrip": false,
182
- "normalized": false,
183
- "special": false
184
- },
185
- "248063": {
186
- "content": "<|fim_pad|>",
187
- "single_word": false,
188
- "lstrip": false,
189
- "rstrip": false,
190
- "normalized": false,
191
- "special": false
192
- },
193
- "248064": {
194
- "content": "<|repo_name|>",
195
- "single_word": false,
196
- "lstrip": false,
197
- "rstrip": false,
198
- "normalized": false,
199
- "special": false
200
- },
201
- "248065": {
202
- "content": "<|file_sep|>",
203
- "single_word": false,
204
- "lstrip": false,
205
- "rstrip": false,
206
- "normalized": false,
207
- "special": false
208
- },
209
- "248066": {
210
- "content": "<tool_response>",
211
- "single_word": false,
212
- "lstrip": false,
213
- "rstrip": false,
214
- "normalized": false,
215
- "special": false
216
- },
217
- "248067": {
218
- "content": "</tool_response>",
219
- "single_word": false,
220
- "lstrip": false,
221
- "rstrip": false,
222
- "normalized": false,
223
- "special": false
224
- },
225
- "248068": {
226
- "content": "<think>",
227
- "single_word": false,
228
- "lstrip": false,
229
- "rstrip": false,
230
- "normalized": false,
231
- "special": false
232
- },
233
- "248069": {
234
- "content": "</think>",
235
- "single_word": false,
236
- "lstrip": false,
237
- "rstrip": false,
238
- "normalized": false,
239
- "special": false
240
- },
241
- "248070": {
242
- "content": "<|audio_start|>",
243
- "single_word": false,
244
- "lstrip": false,
245
- "rstrip": false,
246
- "normalized": false,
247
- "special": true
248
- },
249
- "248071": {
250
- "content": "<|audio_end|>",
251
- "single_word": false,
252
- "lstrip": false,
253
- "rstrip": false,
254
- "normalized": false,
255
- "special": true
256
- },
257
- "248072": {
258
- "content": "<tts_pad>",
259
- "single_word": false,
260
- "lstrip": false,
261
- "rstrip": false,
262
- "normalized": false,
263
- "special": true
264
- },
265
- "248073": {
266
- "content": "<tts_text_bos>",
267
- "single_word": false,
268
- "lstrip": false,
269
- "rstrip": false,
270
- "normalized": false,
271
- "special": true
272
- },
273
- "248074": {
274
- "content": "<tts_text_eod>",
275
- "single_word": false,
276
- "lstrip": false,
277
- "rstrip": false,
278
- "normalized": false,
279
- "special": true
280
- },
281
- "248075": {
282
- "content": "<tts_text_bos_single>",
283
- "single_word": false,
284
- "lstrip": false,
285
- "rstrip": false,
286
- "normalized": false,
287
- "special": true
288
- },
289
- "248076": {
290
- "content": "<|audio_pad|>",
291
- "single_word": false,
292
- "lstrip": false,
293
- "rstrip": false,
294
- "normalized": false,
295
- "special": true
296
- }
297
- }
298
  }
 
21
  "vision_eos_token": "<|vision_end|>"
22
  },
23
  "pad_token": "<|endoftext|>",
 
24
  "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+",
25
+ "processor_class": "Qwen3VLProcessor",
26
  "split_special_tokens": false,
27
  "tokenizer_class": "TokenizersBackend",
28
  "unk_token": null,
29
  "video_token": "<|video_pad|>",
30
  "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }