Hugging Face's logo

Ba2han
/
test_05082

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
Generated from Trainer
sft
unsloth
trl
conversational
Model card Files
xet
 Community
Ba2han commited on
Commit
f29cbe2
·
verified ·
1 Parent(s): 8f32f9b

Training in progress, step 2375, checkpoint

Browse files
Files changed (11) hide show
  1. last-checkpoint/chat_template.jinja +5 -0
  2. last-checkpoint/config.json +108 -0
  3. last-checkpoint/generation_config.json +9 -0
  4. last-checkpoint/model.safetensors +3 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/tokenizer.json +3 -0
  9. last-checkpoint/tokenizer_config.json +302 -0
  10. last-checkpoint/trainer_state.json +0 -0
  11. last-checkpoint/training_args.bin +3 -0
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '
3
+ '}}{% endif %}{% endfor %}
4
+ {% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant
5
+ ' }}{% endif %}
last-checkpoint/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "unsloth/Qwen3.5-2B",
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": null,
17
+ "dtype": "bfloat16",
18
+ "eos_token_id": 248046,
19
+ "full_attention_interval": 4,
20
+ "head_dim": 256,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 2048,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 6144,
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
+ ],
51
+ "linear_conv_kernel_dim": 4,
52
+ "linear_key_head_dim": 128,
53
+ "linear_num_key_heads": 16,
54
+ "linear_num_value_heads": 16,
55
+ "linear_value_head_dim": 128,
56
+ "mamba_ssm_dtype": "float32",
57
+ "max_position_embeddings": 262144,
58
+ "mlp_only_layers": [],
59
+ "model_type": "qwen3_5_text",
60
+ "mtp_num_hidden_layers": 1,
61
+ "mtp_use_dedicated_embeddings": false,
62
+ "num_attention_heads": 8,
63
+ "num_hidden_layers": 24,
64
+ "num_key_value_heads": 2,
65
+ "pad_token_id": 248055,
66
+ "partial_rotary_factor": 0.25,
67
+ "rms_norm_eps": 1e-06,
68
+ "rope_parameters": {
69
+ "mrope_interleaved": true,
70
+ "mrope_section": [
71
+ 11,
72
+ 11,
73
+ 10
74
+ ],
75
+ "partial_rotary_factor": 0.25,
76
+ "rope_theta": 10000000,
77
+ "rope_type": "default"
78
+ },
79
+ "tie_word_embeddings": true,
80
+ "use_cache": false,
81
+ "vocab_size": 248320
82
+ },
83
+ "tie_word_embeddings": true,
84
+ "transformers_version": "5.5.0",
85
+ "unsloth_fixed_mtp": true,
86
+ "unsloth_version": "2026.8.3",
87
+ "use_cache": false,
88
+ "video_token_id": 248057,
89
+ "vision_config": {
90
+ "deepstack_visual_indexes": [],
91
+ "depth": 24,
92
+ "dtype": "bfloat16",
93
+ "hidden_act": "gelu_pytorch_tanh",
94
+ "hidden_size": 1024,
95
+ "in_channels": 3,
96
+ "initializer_range": 0.02,
97
+ "intermediate_size": 4096,
98
+ "model_type": "qwen3_5",
99
+ "num_heads": 16,
100
+ "num_position_embeddings": 2304,
101
+ "out_hidden_size": 2048,
102
+ "patch_size": 16,
103
+ "spatial_merge_size": 2,
104
+ "temporal_patch_size": 2
105
+ },
106
+ "vision_end_token_id": 248054,
107
+ "vision_start_token_id": 248053
108
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248046
5
+ ],
6
+ "pad_token_id": 248055,
7
+ "transformers_version": "5.5.0",
8
+ "use_cache": true
9
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6688a87371daa62facfcc5d2bbb0469e33e312563e8058900fd191575694fb2
3
+ size 4426983440
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8236cbc9a471f24f34abe84b8353976ba136dc252af7b0f240654d8c699e1ffa
3
+ size 1885522763
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ce1406ae3305b579c247f2bc652eb1a67a0fabaf1501dc1076a65c6f9a742cd
3
+ size 14899
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98f7a93e5d666de9205b0569be8f65e592afec3e940e94a5932cc9837ab8f1b5
3
+ size 13113
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5821fc8fd18831c069840bb21a58dcb792c0a6cc469b6e586a94d1a850a2613f
3
+ size 19989441
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": [
12
+ "<|im_start|>"
13
+ ],
14
+ "image_token": "<|image_pad|>",
15
+ "is_local": false,
16
+ "model_max_length": 262144,
17
+ "model_specific_special_tokens": {
18
+ "audio_bos_token": "<|audio_start|>",
19
+ "audio_eos_token": "<|audio_end|>",
20
+ "audio_token": "<|audio_pad|>",
21
+ "image_token": "<|image_pad|>",
22
+ "video_token": "<|video_pad|>",
23
+ "vision_bos_token": "<|vision_start|>",
24
+ "vision_eos_token": "<|vision_end|>"
25
+ },
26
+ "pad_token": "<|vision_pad|>",
27
+ "padding_side": "right",
28
+ "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+",
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "split_special_tokens": false,
31
+ "tokenizer_class": "TokenizersBackend",
32
+ "unk_token": null,
33
+ "video_token": "<|video_pad|>",
34
+ "vision_bos_token": "<|vision_start|>",
35
+ "vision_eos_token": "<|vision_end|>",
36
+ "added_tokens_decoder": {
37
+ "248044": {
38
+ "content": "<|endoftext|>",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": false,
43
+ "special": true
44
+ },
45
+ "248045": {
46
+ "content": "<|im_start|>",
47
+ "single_word": false,
48
+ "lstrip": false,
49
+ "rstrip": false,
50
+ "normalized": false,
51
+ "special": true
52
+ },
53
+ "248046": {
54
+ "content": "<|im_end|>",
55
+ "single_word": false,
56
+ "lstrip": false,
57
+ "rstrip": false,
58
+ "normalized": false,
59
+ "special": true
60
+ },
61
+ "248047": {
62
+ "content": "<|object_ref_start|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ "248048": {
70
+ "content": "<|object_ref_end|>",
71
+ "single_word": false,
72
+ "lstrip": false,
73
+ "rstrip": false,
74
+ "normalized": false,
75
+ "special": true
76
+ },
77
+ "248049": {
78
+ "content": "<|box_start|>",
79
+ "single_word": false,
80
+ "lstrip": false,
81
+ "rstrip": false,
82
+ "normalized": false,
83
+ "special": true
84
+ },
85
+ "248050": {
86
+ "content": "<|box_end|>",
87
+ "single_word": false,
88
+ "lstrip": false,
89
+ "rstrip": false,
90
+ "normalized": false,
91
+ "special": true
92
+ },
93
+ "248051": {
94
+ "content": "<|quad_start|>",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": false,
99
+ "special": true
100
+ },
101
+ "248052": {
102
+ "content": "<|quad_end|>",
103
+ "single_word": false,
104
+ "lstrip": false,
105
+ "rstrip": false,
106
+ "normalized": false,
107
+ "special": true
108
+ },
109
+ "248053": {
110
+ "content": "<|vision_start|>",
111
+ "single_word": false,
112
+ "lstrip": false,
113
+ "rstrip": false,
114
+ "normalized": false,
115
+ "special": true
116
+ },
117
+ "248054": {
118
+ "content": "<|vision_end|>",
119
+ "single_word": false,
120
+ "lstrip": false,
121
+ "rstrip": false,
122
+ "normalized": false,
123
+ "special": true
124
+ },
125
+ "248055": {
126
+ "content": "<|vision_pad|>",
127
+ "single_word": false,
128
+ "lstrip": false,
129
+ "rstrip": false,
130
+ "normalized": false,
131
+ "special": true
132
+ },
133
+ "248056": {
134
+ "content": "<|image_pad|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ "248057": {
142
+ "content": "<|video_pad|>",
143
+ "single_word": false,
144
+ "lstrip": false,
145
+ "rstrip": false,
146
+ "normalized": false,
147
+ "special": true
148
+ },
149
+ "248058": {
150
+ "content": "<tool_call>",
151
+ "single_word": false,
152
+ "lstrip": false,
153
+ "rstrip": false,
154
+ "normalized": false,
155
+ "special": false
156
+ },
157
+ "248059": {
158
+ "content": "</tool_call>",
159
+ "single_word": false,
160
+ "lstrip": false,
161
+ "rstrip": false,
162
+ "normalized": false,
163
+ "special": false
164
+ },
165
+ "248060": {
166
+ "content": "<|fim_prefix|>",
167
+ "single_word": false,
168
+ "lstrip": false,
169
+ "rstrip": false,
170
+ "normalized": false,
171
+ "special": false
172
+ },
173
+ "248061": {
174
+ "content": "<|fim_middle|>",
175
+ "single_word": false,
176
+ "lstrip": false,
177
+ "rstrip": false,
178
+ "normalized": false,
179
+ "special": false
180
+ },
181
+ "248062": {
182
+ "content": "<|fim_suffix|>",
183
+ "single_word": false,
184
+ "lstrip": false,
185
+ "rstrip": false,
186
+ "normalized": false,
187
+ "special": false
188
+ },
189
+ "248063": {
190
+ "content": "<|fim_pad|>",
191
+ "single_word": false,
192
+ "lstrip": false,
193
+ "rstrip": false,
194
+ "normalized": false,
195
+ "special": false
196
+ },
197
+ "248064": {
198
+ "content": "<|repo_name|>",
199
+ "single_word": false,
200
+ "lstrip": false,
201
+ "rstrip": false,
202
+ "normalized": false,
203
+ "special": false
204
+ },
205
+ "248065": {
206
+ "content": "<|file_sep|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": false
212
+ },
213
+ "248066": {
214
+ "content": "<tool_response>",
215
+ "single_word": false,
216
+ "lstrip": false,
217
+ "rstrip": false,
218
+ "normalized": false,
219
+ "special": false
220
+ },
221
+ "248067": {
222
+ "content": "</tool_response>",
223
+ "single_word": false,
224
+ "lstrip": false,
225
+ "rstrip": false,
226
+ "normalized": false,
227
+ "special": false
228
+ },
229
+ "248068": {
230
+ "content": "<think>",
231
+ "single_word": false,
232
+ "lstrip": false,
233
+ "rstrip": false,
234
+ "normalized": false,
235
+ "special": false
236
+ },
237
+ "248069": {
238
+ "content": "</think>",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": false,
243
+ "special": false
244
+ },
245
+ "248070": {
246
+ "content": "<|audio_start|>",
247
+ "single_word": false,
248
+ "lstrip": false,
249
+ "rstrip": false,
250
+ "normalized": false,
251
+ "special": true
252
+ },
253
+ "248071": {
254
+ "content": "<|audio_end|>",
255
+ "single_word": false,
256
+ "lstrip": false,
257
+ "rstrip": false,
258
+ "normalized": false,
259
+ "special": true
260
+ },
261
+ "248072": {
262
+ "content": "<tts_pad>",
263
+ "single_word": false,
264
+ "lstrip": false,
265
+ "rstrip": false,
266
+ "normalized": false,
267
+ "special": true
268
+ },
269
+ "248073": {
270
+ "content": "<tts_text_bos>",
271
+ "single_word": false,
272
+ "lstrip": false,
273
+ "rstrip": false,
274
+ "normalized": false,
275
+ "special": true
276
+ },
277
+ "248074": {
278
+ "content": "<tts_text_eod>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ "248075": {
286
+ "content": "<tts_text_bos_single>",
287
+ "single_word": false,
288
+ "lstrip": false,
289
+ "rstrip": false,
290
+ "normalized": false,
291
+ "special": true
292
+ },
293
+ "248076": {
294
+ "content": "<|audio_pad|>",
295
+ "single_word": false,
296
+ "lstrip": false,
297
+ "rstrip": false,
298
+ "normalized": false,
299
+ "special": true
300
+ }
301
+ }
302
+ }
last-checkpoint/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee5d8885e7287907836811a25a5c589cde713ec3cdf450d761d204b4c0e2351
3
+ size 5777