Hugging Face's logo

maci0
/
Qwopus3.6-27B-Coder-NVFP4

Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5
nvfp4
fp4
w4a4
gptq
quantized
compressed-tensors
llm-compressor
vllm
vision-language
thinking
code
coder
conversational
8-bit precision
Model card Files
xet
 Community
1
maci0 commited on
Commit
9f17f98
·
verified ·
1 Parent(s): 011bebd

NVFP4 quant (GPTQ, MSE, shared fused-layer scales)

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +144 -0
  3. config.json +292 -0
  4. generation_config.json +13 -0
  5. model.safetensors +3 -0
  6. processor_config.json +64 -0
  7. recipe.yaml +12 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +34 -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
chat_template.jinja ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ {%- if tools %}
3
+ {{- '<|im_start|>system
4
+ ' }}
5
+ {%- if messages[0].role == 'system' %}
6
+ {{- messages[0].content + '
7
+
8
+ ' }}
9
+ {%- endif %}
10
+ {{- "# Tools
11
+
12
+ You may call one or more functions to assist with the user query.
13
+
14
+ You are provided with function signatures within <tools></tools> XML tags:
15
+ <tools>" }}
16
+ {%- for tool in tools %}
17
+ {{- "
18
+ " }}
19
+ {{- tool | tojson }}
20
+ {%- endfor %}
21
+ {{- "
22
+ </tools>
23
+
24
+ For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
25
+ <tool_call>
26
+ {\"name\": <function-name>, \"arguments\": <args-json-object>}
27
+ </tool_call><|im_end|>
28
+ " }}
29
+ {%- else %}
30
+ {%- if messages[0].role == 'system' %}
31
+ {{- '<|im_start|>system
32
+ ' + messages[0].content + '<|im_end|>
33
+ ' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
37
+ {%- for forward_message in messages %}
38
+ {%- set index = (messages|length - 1) - loop.index0 %}
39
+ {%- set message = messages[index] %}
40
+ {%- set current_content = message.content if message.content is not none else '' %}
41
+ {%- set tool_start = '<tool_response>' %}
42
+ {%- set tool_start_length = tool_start|length %}
43
+ {%- set start_of_message = current_content[:tool_start_length] %}
44
+ {%- set tool_end = '</tool_response>' %}
45
+ {%- set tool_end_length = tool_end|length %}
46
+ {%- set start_pos = (current_content|length) - tool_end_length %}
47
+ {%- if start_pos < 0 %}
48
+ {%- set start_pos = 0 %}
49
+ {%- endif %}
50
+ {%- set end_of_message = current_content[start_pos:] %}
51
+ {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
52
+ {%- set ns.multi_step_tool = false %}
53
+ {%- set ns.last_query_index = index %}
54
+ {%- endif %}
55
+ {%- endfor %}
56
+ {%- for message in messages %}
57
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
58
+ {{- '<|im_start|>' + message.role + '
59
+ ' + message.content + '<|im_end|>' + '
60
+ ' }}
61
+ {%- elif message.role == "assistant" %}
62
+ {%- set content = message.content %}
63
+ {%- set reasoning_content = '' %}
64
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
65
+ {%- set reasoning_content = message.reasoning_content %}
66
+ {%- else %}
67
+ {%- if '</think>' in message.content %}
68
+ {%- set content = (message.content.split('</think>')|last).lstrip('
69
+ ') %}
70
+ {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('
71
+ ') %}
72
+ {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('
73
+ ') %}
74
+ {%- endif %}
75
+ {%- endif %}
76
+ {%- if loop.index0 > ns.last_query_index %}
77
+ {%- if loop.last or (not loop.last and reasoning_content) %}
78
+ {{- '<|im_start|>' + message.role + '
79
+ <think>
80
+ ' + reasoning_content.strip('
81
+ ') + '
82
+ </think>
83
+
84
+ ' + content.lstrip('
85
+ ') }}
86
+ {%- else %}
87
+ {{- '<|im_start|>' + message.role + '
88
+ ' + content }}
89
+ {%- endif %}
90
+ {%- else %}
91
+ {{- '<|im_start|>' + message.role + '
92
+ ' + content }}
93
+ {%- endif %}
94
+ {%- if message.tool_calls %}
95
+ {%- for tool_call in message.tool_calls %}
96
+ {%- if (loop.first and content) or (not loop.first) %}
97
+ {{- '
98
+ ' }}
99
+ {%- endif %}
100
+ {%- if tool_call.function %}
101
+ {%- set tool_call = tool_call.function %}
102
+ {%- endif %}
103
+ {{- '<tool_call>
104
+ {"name": "' }}
105
+ {{- tool_call.name }}
106
+ {{- '", "arguments": ' }}
107
+ {%- if tool_call.arguments is string %}
108
+ {{- tool_call.arguments }}
109
+ {%- else %}
110
+ {{- tool_call.arguments | tojson }}
111
+ {%- endif %}
112
+ {{- '}
113
+ </tool_call>' }}
114
+ {%- endfor %}
115
+ {%- endif %}
116
+ {{- '<|im_end|>
117
+ ' }}
118
+ {%- elif message.role == "tool" %}
119
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
120
+ {{- '<|im_start|>user' }}
121
+ {%- endif %}
122
+ {{- '
123
+ <tool_response>
124
+ ' }}
125
+ {{- message.content }}
126
+ {{- '
127
+ </tool_response>' }}
128
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
129
+ {{- '<|im_end|>
130
+ ' }}
131
+ {%- endif %}
132
+ {%- endif %}
133
+ {%- endfor %}
134
+ {%- if add_generation_prompt %}
135
+ {{- '<|im_start|>assistant
136
+ ' }}
137
+ {%- if enable_thinking is defined and enable_thinking is false %}
138
+ {{- '<think>
139
+
140
+ </think>
141
+
142
+ ' }}
143
+ {%- endif %}
144
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "torch_dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "language_model_only": false,
8
+ "model_name": "Unsloth/qwen3.6-27B",
9
+ "model_type": "qwen3_5",
10
+ "mtp_num_hidden_layers": 1,
11
+ "pad_token_id": 248055,
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_output_gate": true,
16
+ "bos_token_id": 248044,
17
+ "torch_dtype": "bfloat16",
18
+ "eos_token_id": 248044,
19
+ "full_attention_interval": 4,
20
+ "head_dim": 256,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 5120,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 17408,
25
+ "layer_types": [
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
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
+ ],
91
+ "linear_conv_kernel_dim": 4,
92
+ "linear_key_head_dim": 128,
93
+ "linear_num_key_heads": 16,
94
+ "linear_num_value_heads": 48,
95
+ "linear_value_head_dim": 128,
96
+ "mamba_ssm_dtype": "float32",
97
+ "max_position_embeddings": 262144,
98
+ "model_type": "qwen3_5_text",
99
+ "mtp_num_hidden_layers": 1,
100
+ "mtp_use_dedicated_embeddings": false,
101
+ "num_attention_heads": 24,
102
+ "num_hidden_layers": 64,
103
+ "num_key_value_heads": 4,
104
+ "output_gate_type": "swish",
105
+ "pad_token_id": null,
106
+ "partial_rotary_factor": 0.25,
107
+ "rms_norm_eps": 1e-06,
108
+ "rope_parameters": {
109
+ "mrope_interleaved": true,
110
+ "mrope_section": [
111
+ 11,
112
+ 11,
113
+ 10
114
+ ],
115
+ "partial_rotary_factor": 0.25,
116
+ "rope_theta": 10000000,
117
+ "rope_type": "default"
118
+ },
119
+ "tie_word_embeddings": false,
120
+ "use_cache": true,
121
+ "vocab_size": 248320
122
+ },
123
+ "tie_word_embeddings": false,
124
+ "unsloth_fixed_mtp": true,
125
+ "unsloth_version": "2026.5.9",
126
+ "video_token_id": 248057,
127
+ "vision_config": {
128
+ "deepstack_visual_indexes": [],
129
+ "depth": 27,
130
+ "torch_dtype": "bfloat16",
131
+ "hidden_act": "gelu_pytorch_tanh",
132
+ "hidden_size": 1152,
133
+ "in_channels": 3,
134
+ "initializer_range": 0.02,
135
+ "intermediate_size": 4304,
136
+ "model_type": "qwen3_5",
137
+ "num_heads": 16,
138
+ "num_position_embeddings": 2304,
139
+ "out_hidden_size": 5120,
140
+ "patch_size": 16,
141
+ "spatial_merge_size": 2,
142
+ "temporal_patch_size": 2
143
+ },
144
+ "vision_end_token_id": 248054,
145
+ "vision_start_token_id": 248053,
146
+ "quantization_config": {
147
+ "config_groups": {
148
+ "group_0": {
149
+ "format": "nvfp4-pack-quantized",
150
+ "input_activations": {
151
+ "actorder": null,
152
+ "block_structure": null,
153
+ "dynamic": "local",
154
+ "group_size": 16,
155
+ "num_bits": 4,
156
+ "observer": "static_minmax",
157
+ "observer_kwargs": {},
158
+ "scale_dtype": "torch.float8_e4m3fn",
159
+ "strategy": "tensor_group",
160
+ "symmetric": true,
161
+ "type": "float",
162
+ "zp_dtype": null
163
+ },
164
+ "output_activations": null,
165
+ "targets": [
166
+ "Linear"
167
+ ],
168
+ "weights": {
169
+ "actorder": "static",
170
+ "block_structure": null,
171
+ "dynamic": false,
172
+ "group_size": 16,
173
+ "num_bits": 4,
174
+ "observer": "mse",
175
+ "observer_kwargs": {},
176
+ "scale_dtype": "torch.float8_e4m3fn",
177
+ "strategy": "tensor_group",
178
+ "symmetric": true,
179
+ "type": "float",
180
+ "zp_dtype": null
181
+ }
182
+ }
183
+ },
184
+ "format": "nvfp4-pack-quantized",
185
+ "global_compression_ratio": null,
186
+ "ignore": [
187
+ "model.layers.0.linear_attn",
188
+ "model.layers.0.linear_attn.norm",
189
+ "model.layers.1.linear_attn",
190
+ "model.layers.1.linear_attn.norm",
191
+ "model.layers.2.linear_attn",
192
+ "model.layers.2.linear_attn.norm",
193
+ "model.layers.4.linear_attn",
194
+ "model.layers.4.linear_attn.norm",
195
+ "model.layers.5.linear_attn",
196
+ "model.layers.5.linear_attn.norm",
197
+ "model.layers.6.linear_attn",
198
+ "model.layers.6.linear_attn.norm",
199
+ "model.layers.8.linear_attn",
200
+ "model.layers.8.linear_attn.norm",
201
+ "model.layers.9.linear_attn",
202
+ "model.layers.9.linear_attn.norm",
203
+ "model.layers.10.linear_attn",
204
+ "model.layers.10.linear_attn.norm",
205
+ "model.layers.12.linear_attn",
206
+ "model.layers.12.linear_attn.norm",
207
+ "model.layers.13.linear_attn",
208
+ "model.layers.13.linear_attn.norm",
209
+ "model.layers.14.linear_attn",
210
+ "model.layers.14.linear_attn.norm",
211
+ "model.layers.16.linear_attn",
212
+ "model.layers.16.linear_attn.norm",
213
+ "model.layers.17.linear_attn",
214
+ "model.layers.17.linear_attn.norm",
215
+ "model.layers.18.linear_attn",
216
+ "model.layers.18.linear_attn.norm",
217
+ "model.layers.20.linear_attn",
218
+ "model.layers.20.linear_attn.norm",
219
+ "model.layers.21.linear_attn",
220
+ "model.layers.21.linear_attn.norm",
221
+ "model.layers.22.linear_attn",
222
+ "model.layers.22.linear_attn.norm",
223
+ "model.layers.24.linear_attn",
224
+ "model.layers.24.linear_attn.norm",
225
+ "model.layers.25.linear_attn",
226
+ "model.layers.25.linear_attn.norm",
227
+ "model.layers.26.linear_attn",
228
+ "model.layers.26.linear_attn.norm",
229
+ "model.layers.28.linear_attn",
230
+ "model.layers.28.linear_attn.norm",
231
+ "model.layers.29.linear_attn",
232
+ "model.layers.29.linear_attn.norm",
233
+ "model.layers.30.linear_attn",
234
+ "model.layers.30.linear_attn.norm",
235
+ "model.layers.32.linear_attn",
236
+ "model.layers.32.linear_attn.norm",
237
+ "model.layers.33.linear_attn",
238
+ "model.layers.33.linear_attn.norm",
239
+ "model.layers.34.linear_attn",
240
+ "model.layers.34.linear_attn.norm",
241
+ "model.layers.36.linear_attn",
242
+ "model.layers.36.linear_attn.norm",
243
+ "model.layers.37.linear_attn",
244
+ "model.layers.37.linear_attn.norm",
245
+ "model.layers.38.linear_attn",
246
+ "model.layers.38.linear_attn.norm",
247
+ "model.layers.40.linear_attn",
248
+ "model.layers.40.linear_attn.norm",
249
+ "model.layers.41.linear_attn",
250
+ "model.layers.41.linear_attn.norm",
251
+ "model.layers.42.linear_attn",
252
+ "model.layers.42.linear_attn.norm",
253
+ "model.layers.44.linear_attn",
254
+ "model.layers.44.linear_attn.norm",
255
+ "model.layers.45.linear_attn",
256
+ "model.layers.45.linear_attn.norm",
257
+ "model.layers.46.linear_attn",
258
+ "model.layers.46.linear_attn.norm",
259
+ "model.layers.48.linear_attn",
260
+ "model.layers.48.linear_attn.norm",
261
+ "model.layers.49.linear_attn",
262
+ "model.layers.49.linear_attn.norm",
263
+ "model.layers.50.linear_attn",
264
+ "model.layers.50.linear_attn.norm",
265
+ "model.layers.52.linear_attn",
266
+ "model.layers.52.linear_attn.norm",
267
+ "model.layers.53.linear_attn",
268
+ "model.layers.53.linear_attn.norm",
269
+ "model.layers.54.linear_attn",
270
+ "model.layers.54.linear_attn.norm",
271
+ "model.layers.56.linear_attn",
272
+ "model.layers.56.linear_attn.norm",
273
+ "model.layers.57.linear_attn",
274
+ "model.layers.57.linear_attn.norm",
275
+ "model.layers.58.linear_attn",
276
+ "model.layers.58.linear_attn.norm",
277
+ "model.layers.60.linear_attn",
278
+ "model.layers.60.linear_attn.norm",
279
+ "model.layers.61.linear_attn",
280
+ "model.layers.61.linear_attn.norm",
281
+ "model.layers.62.linear_attn",
282
+ "model.layers.62.linear_attn.norm",
283
+ "lm_head"
284
+ ],
285
+ "kv_cache_scheme": null,
286
+ "quant_method": "compressed-tensors",
287
+ "quantization_status": "compressed",
288
+ "sparsity_config": {},
289
+ "transform_config": {},
290
+ "version": "0.17.1"
291
+ }
292
+ }
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": 248055,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.12.1"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad3b359de16e311cc501c01fcb6bdbbb3628b903a493f1e9af6e77f6af6fe82
3
+ size 18788385784
processor_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "do_convert_rgb": true,
6
+ "do_normalize": true,
7
+ "do_rescale": true,
8
+ "do_resize": true,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_processor_type": "Qwen2VLImageProcessor",
15
+ "image_std": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "merge_size": 2,
21
+ "patch_size": 16,
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 16777216,
26
+ "shortest_edge": 65536
27
+ },
28
+ "temporal_patch_size": 2
29
+ },
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "video_processor": {
32
+ "data_format": "channels_first",
33
+ "default_to_square": true,
34
+ "do_convert_rgb": true,
35
+ "do_normalize": true,
36
+ "do_rescale": true,
37
+ "do_resize": true,
38
+ "do_sample_frames": true,
39
+ "fps": 2,
40
+ "image_mean": [
41
+ 0.5,
42
+ 0.5,
43
+ 0.5
44
+ ],
45
+ "image_std": [
46
+ 0.5,
47
+ 0.5,
48
+ 0.5
49
+ ],
50
+ "max_frames": 768,
51
+ "merge_size": 2,
52
+ "min_frames": 4,
53
+ "patch_size": 16,
54
+ "resample": 3,
55
+ "rescale_factor": 0.00392156862745098,
56
+ "return_metadata": false,
57
+ "size": {
58
+ "longest_edge": 25165824,
59
+ "shortest_edge": 4096
60
+ },
61
+ "temporal_patch_size": 2,
62
+ "video_processor_type": "Qwen3VLVideoProcessor"
63
+ }
64
+ }
recipe.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ GPTQModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*visual.*', 're:.*mtp.*']
6
+ scheme: NVFP4
7
+ observer: {weights: mse}
8
+ bypass_divisibility_checks: false
9
+ block_size: 128
10
+ dampening_frac: 0.01
11
+ actorder: static
12
+ offload_hessians: false
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|vision_pad|>",
25
+ "padding_side": "left",
26
+ "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+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "TokenizersBackend",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }