tomngdev commited on
Commit
64eb0e3
·
verified ·
1 Parent(s): ca457a8

Upload folder using huggingface_hub

Browse files
.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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- macro render_content(content, is_system_content=false) %}
2
+ {%- if content is string %}
3
+ {{- content }}
4
+ {%- elif content is iterable and content is not mapping %}
5
+ {%- for item in content %}
6
+ {%- if 'text' in item %}
7
+ {{- item.text }}
8
+ {%- else %}
9
+ {{- raise_exception('Unexpected item type in content.') }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- elif content is none or content is undefined %}
13
+ {{- '' }}
14
+ {%- else %}
15
+ {{- raise_exception('Unexpected content type.') }}
16
+ {%- endif %}
17
+ {%- endmacro %}
18
+ {%- if not messages %}
19
+ {{- raise_exception('No messages provided.') }}
20
+ {%- endif %}
21
+ {%- if messages[0].role == 'system' %}
22
+ {%- set system_content = render_content(messages[0].content, true)|trim %}
23
+ {{- '<|im_start|>system
24
+ ' + system_content + '<|im_end|>
25
+ ' }}
26
+ {%- endif %}
27
+ {%- for message in messages %}
28
+ {%- set content = render_content(message.content)|trim %}
29
+ {%- if message.role == "system" %}
30
+ {%- if not loop.first %}
31
+ {{- raise_exception('System message must be at the beginning.') }}
32
+ {%- endif %}
33
+ {%- elif message.role == "user" or message.role == "assistant" %}
34
+ {{- '<|im_start|>' + message.role + '
35
+ ' + content + '<|im_end|>
36
+ ' }}
37
+ {%- else %}
38
+ {{- raise_exception('Unexpected message role.') }}
39
+ {%- endif %}
40
+ {%- endfor %}
41
+ {%- if add_generation_prompt %}
42
+ {{- '<|im_start|>assistant
43
+ ' }}
44
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248044,
7
+ "image_token_id": 248056,
8
+ "model_name": "Qwen/Qwen3.5-0.8B-Base",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248055,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "attn_output_gate": true,
15
+ "bos_token_id": null,
16
+ "dtype": "bfloat16",
17
+ "eos_token_id": 248044,
18
+ "full_attention_interval": 4,
19
+ "head_dim": 256,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 1024,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3584,
24
+ "layer_types": [
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention"
49
+ ],
50
+ "linear_conv_kernel_dim": 4,
51
+ "linear_key_head_dim": 128,
52
+ "linear_num_key_heads": 16,
53
+ "linear_num_value_heads": 16,
54
+ "linear_value_head_dim": 128,
55
+ "mamba_ssm_dtype": "float32",
56
+ "max_position_embeddings": 262144,
57
+ "mlp_only_layers": [],
58
+ "model_type": "qwen3_5_text",
59
+ "mtp_num_hidden_layers": 1,
60
+ "mtp_use_dedicated_embeddings": false,
61
+ "num_attention_heads": 8,
62
+ "num_hidden_layers": 24,
63
+ "num_key_value_heads": 2,
64
+ "pad_token_id": null,
65
+ "partial_rotary_factor": 0.25,
66
+ "rms_norm_eps": 1e-06,
67
+ "rope_parameters": {
68
+ "mrope_interleaved": true,
69
+ "mrope_section": [
70
+ 11,
71
+ 11,
72
+ 10
73
+ ],
74
+ "partial_rotary_factor": 0.25,
75
+ "rope_theta": 10000000,
76
+ "rope_type": "default"
77
+ },
78
+ "tie_word_embeddings": true,
79
+ "use_cache": true,
80
+ "vocab_size": 248320
81
+ },
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.5.0",
84
+ "unsloth_version": "2026.8.18",
85
+ "use_cache": false,
86
+ "video_token_id": 248057,
87
+ "vision_config": {
88
+ "deepstack_visual_indexes": [],
89
+ "depth": 12,
90
+ "dtype": "bfloat16",
91
+ "hidden_act": "gelu_pytorch_tanh",
92
+ "hidden_size": 768,
93
+ "in_channels": 3,
94
+ "initializer_range": 0.02,
95
+ "intermediate_size": 3072,
96
+ "model_type": "qwen3_5",
97
+ "num_heads": 12,
98
+ "num_position_embeddings": 2304,
99
+ "out_hidden_size": 1024,
100
+ "patch_size": 16,
101
+ "spatial_merge_size": 2,
102
+ "temporal_patch_size": 2
103
+ },
104
+ "vision_end_token_id": 248054,
105
+ "vision_start_token_id": 248053
106
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248044,
5
+ 248044
6
+ ],
7
+ "pad_token_id": 248055,
8
+ "transformers_version": "5.5.0",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b89ab61e674382800e825b7863515f69918d735b39389dea034fe5d47131a130
3
+ size 1706229168
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 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
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|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|vision_pad|>",
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
+ }