Image-Text-to-Text
English
conversational
shiym2000 commited on
Commit
46a0b6b
·
verified ·
1 Parent(s): aac5624

Upload 6 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,408 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cache_dir_hf": "~/.cache/huggingface",
3
+ "exp_id": 4,
4
+ "hidden_size": 3072,
5
+ "llm_attn_implementation": "flash_attention_2",
6
+ "llm_config": {
7
+ "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "Phi3ForCausalLM"
11
+ ],
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "auto_map": {
15
+ "AutoConfig": "configuration_phi3.Phi3Config",
16
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
17
+ "AutoModelForSequenceClassification": "modeling_phi3.Phi3ForSequenceClassification",
18
+ "AutoModelForTokenClassification": "modeling_phi3.Phi3ForTokenClassification"
19
+ },
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 1,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "embd_pdrop": 0.0,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 32000,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_act": "silu",
37
+ "hidden_size": 3072,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 8192,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "max_position_embeddings": 131072,
53
+ "min_length": 0,
54
+ "model_type": "phi3",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_attention_heads": 32,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 32,
60
+ "num_key_value_heads": 32,
61
+ "num_return_sequences": 1,
62
+ "original_max_position_embeddings": 4096,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 32000,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "resid_pdrop": 0.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "rms_norm_eps": 1e-05,
76
+ "rope_scaling": {
77
+ "long_factor": [
78
+ 1.0299999713897705,
79
+ 1.0499999523162842,
80
+ 1.0499999523162842,
81
+ 1.0799999237060547,
82
+ 1.2299998998641968,
83
+ 1.2299998998641968,
84
+ 1.2999999523162842,
85
+ 1.4499999284744263,
86
+ 1.5999999046325684,
87
+ 1.6499998569488525,
88
+ 1.8999998569488525,
89
+ 2.859999895095825,
90
+ 3.68999981880188,
91
+ 5.419999599456787,
92
+ 5.489999771118164,
93
+ 5.489999771118164,
94
+ 9.09000015258789,
95
+ 11.579999923706055,
96
+ 15.65999984741211,
97
+ 15.769999504089355,
98
+ 15.789999961853027,
99
+ 18.360000610351562,
100
+ 21.989999771118164,
101
+ 23.079999923706055,
102
+ 30.009998321533203,
103
+ 32.35000228881836,
104
+ 32.590003967285156,
105
+ 35.56000518798828,
106
+ 39.95000457763672,
107
+ 53.840003967285156,
108
+ 56.20000457763672,
109
+ 57.95000457763672,
110
+ 59.29000473022461,
111
+ 59.77000427246094,
112
+ 59.920005798339844,
113
+ 61.190006256103516,
114
+ 61.96000671386719,
115
+ 62.50000762939453,
116
+ 63.3700065612793,
117
+ 63.48000717163086,
118
+ 63.48000717163086,
119
+ 63.66000747680664,
120
+ 63.850006103515625,
121
+ 64.08000946044922,
122
+ 64.760009765625,
123
+ 64.80001068115234,
124
+ 64.81001281738281,
125
+ 64.81001281738281
126
+ ],
127
+ "short_factor": [
128
+ 1.05,
129
+ 1.05,
130
+ 1.05,
131
+ 1.1,
132
+ 1.1,
133
+ 1.1500000000000001,
134
+ 1.2000000000000002,
135
+ 1.2500000000000002,
136
+ 1.3000000000000003,
137
+ 1.3500000000000003,
138
+ 1.5000000000000004,
139
+ 2.000000000000001,
140
+ 2.000000000000001,
141
+ 2.000000000000001,
142
+ 2.000000000000001,
143
+ 2.000000000000001,
144
+ 2.000000000000001,
145
+ 2.000000000000001,
146
+ 2.000000000000001,
147
+ 2.000000000000001,
148
+ 2.000000000000001,
149
+ 2.000000000000001,
150
+ 2.000000000000001,
151
+ 2.000000000000001,
152
+ 2.000000000000001,
153
+ 2.000000000000001,
154
+ 2.000000000000001,
155
+ 2.000000000000001,
156
+ 2.000000000000001,
157
+ 2.000000000000001,
158
+ 2.000000000000001,
159
+ 2.000000000000001,
160
+ 2.0500000000000007,
161
+ 2.0500000000000007,
162
+ 2.0500000000000007,
163
+ 2.1000000000000005,
164
+ 2.1000000000000005,
165
+ 2.1000000000000005,
166
+ 2.1500000000000004,
167
+ 2.1500000000000004,
168
+ 2.3499999999999996,
169
+ 2.549999999999999,
170
+ 2.5999999999999988,
171
+ 2.5999999999999988,
172
+ 2.7499999999999982,
173
+ 2.849999999999998,
174
+ 2.849999999999998,
175
+ 2.9499999999999975
176
+ ],
177
+ "type": "su"
178
+ },
179
+ "rope_theta": 10000.0,
180
+ "sep_token_id": null,
181
+ "sliding_window": 262144,
182
+ "suppress_tokens": null,
183
+ "task_specific_params": null,
184
+ "temperature": 1.0,
185
+ "tf_legacy_loss": false,
186
+ "tie_encoder_decoder": false,
187
+ "tie_word_embeddings": false,
188
+ "tokenizer_class": null,
189
+ "top_k": 50,
190
+ "top_p": 1.0,
191
+ "torch_dtype": "bfloat16",
192
+ "torchscript": false,
193
+ "typical_p": 1.0,
194
+ "use_bfloat16": false,
195
+ "use_cache": true,
196
+ "vocab_size": 32064
197
+ },
198
+ "llm_max_length": 768,
199
+ "llm_padding_side": "right",
200
+ "llm_type": "phi3",
201
+ "tokenizer_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
202
+ "tokenizer_use_fast": false,
203
+ "transformers_version": "4.42.4",
204
+ "use_cache": false,
205
+ "vision2d_connector_config": {
206
+ "connector_type": "mlp2x_gelu",
207
+ "img_size": [
208
+ 256,
209
+ 256
210
+ ],
211
+ "input_dim": 1024,
212
+ "model_type": "",
213
+ "output_dim": 3072,
214
+ "patch_size": [
215
+ 16,
216
+ 16
217
+ ]
218
+ },
219
+ "vision2d_connector_type": "mlp2x_gelu",
220
+ "vision2d_model_config": {
221
+ "_name_or_path": "google/siglip-large-patch16-256",
222
+ "add_cross_attention": false,
223
+ "architectures": null,
224
+ "attention_dropout": 0.0,
225
+ "bad_words_ids": null,
226
+ "begin_suppress_tokens": null,
227
+ "bos_token_id": null,
228
+ "chunk_size_feed_forward": 0,
229
+ "cross_attention_hidden_size": null,
230
+ "decoder_start_token_id": null,
231
+ "diversity_penalty": 0.0,
232
+ "do_sample": false,
233
+ "early_stopping": false,
234
+ "encoder_no_repeat_ngram_size": 0,
235
+ "eos_token_id": null,
236
+ "exponential_decay_length_penalty": null,
237
+ "finetuning_task": null,
238
+ "forced_bos_token_id": null,
239
+ "forced_eos_token_id": null,
240
+ "hidden_act": "gelu_pytorch_tanh",
241
+ "hidden_size": 1024,
242
+ "id2label": {
243
+ "0": "LABEL_0",
244
+ "1": "LABEL_1"
245
+ },
246
+ "image_size": 256,
247
+ "intermediate_size": 4096,
248
+ "is_decoder": false,
249
+ "is_encoder_decoder": false,
250
+ "label2id": {
251
+ "LABEL_0": 0,
252
+ "LABEL_1": 1
253
+ },
254
+ "layer_norm_eps": 1e-06,
255
+ "length_penalty": 1.0,
256
+ "max_length": 20,
257
+ "min_length": 0,
258
+ "model_type": "siglip_vision_model",
259
+ "no_repeat_ngram_size": 0,
260
+ "num_attention_heads": 16,
261
+ "num_beam_groups": 1,
262
+ "num_beams": 1,
263
+ "num_channels": 3,
264
+ "num_hidden_layers": 24,
265
+ "num_return_sequences": 1,
266
+ "output_attentions": false,
267
+ "output_hidden_states": false,
268
+ "output_scores": false,
269
+ "pad_token_id": null,
270
+ "patch_size": 16,
271
+ "prefix": null,
272
+ "problem_type": null,
273
+ "pruned_heads": {},
274
+ "remove_invalid_values": false,
275
+ "repetition_penalty": 1.0,
276
+ "return_dict": true,
277
+ "return_dict_in_generate": false,
278
+ "sep_token_id": null,
279
+ "suppress_tokens": null,
280
+ "task_specific_params": null,
281
+ "temperature": 1.0,
282
+ "tf_legacy_loss": false,
283
+ "tie_encoder_decoder": false,
284
+ "tie_word_embeddings": true,
285
+ "tokenizer_class": null,
286
+ "top_k": 50,
287
+ "top_p": 1.0,
288
+ "torch_dtype": null,
289
+ "torchscript": false,
290
+ "typical_p": 1.0,
291
+ "use_bfloat16": false
292
+ },
293
+ "vision2d_model_select_feature": "cls_patch",
294
+ "vision2d_model_select_layer": -1,
295
+ "vision2d_model_type": "siglip",
296
+ "vision3d_connector_config": {
297
+ "connector_type": "spatial_pooling_score15_mlp2x_gelu",
298
+ "img_size": [
299
+ 32,
300
+ 256,
301
+ 256
302
+ ],
303
+ "input_dim": 768,
304
+ "model_type": "",
305
+ "output_dim": 3072,
306
+ "patch_size": [
307
+ 4,
308
+ 16,
309
+ 16
310
+ ]
311
+ },
312
+ "vision3d_connector_type": "spatial_pooling_score15_mlp2x_gelu",
313
+ "vision3d_model_config": {
314
+ "_name_or_path": "GoodBaiBai88/M3D-CLIP",
315
+ "add_cross_attention": false,
316
+ "architectures": [
317
+ "M3DCLIP"
318
+ ],
319
+ "auto_map": {
320
+ "AutoConfig": "GoodBaiBai88/M3D-CLIP--configuration_m3d_clip.M3DCLIPConfig",
321
+ "AutoModel": "GoodBaiBai88/M3D-CLIP--modeling_m3d_clip.M3DCLIP"
322
+ },
323
+ "bad_words_ids": null,
324
+ "begin_suppress_tokens": null,
325
+ "bos_token_id": null,
326
+ "chunk_size_feed_forward": 0,
327
+ "cross_attention_hidden_size": null,
328
+ "decoder_start_token_id": null,
329
+ "diversity_penalty": 0.0,
330
+ "do_sample": false,
331
+ "dropout_rate": 0,
332
+ "early_stopping": false,
333
+ "encoder_no_repeat_ngram_size": 0,
334
+ "eos_token_id": null,
335
+ "exponential_decay_length_penalty": null,
336
+ "finetuning_task": null,
337
+ "forced_bos_token_id": null,
338
+ "forced_eos_token_id": null,
339
+ "gather_loss": true,
340
+ "hidden_size": 768,
341
+ "id2label": {
342
+ "0": "LABEL_0",
343
+ "1": "LABEL_1"
344
+ },
345
+ "img_size": [
346
+ 32,
347
+ 256,
348
+ 256
349
+ ],
350
+ "in_channels": 1,
351
+ "is_decoder": false,
352
+ "is_encoder_decoder": false,
353
+ "label2id": {
354
+ "LABEL_0": 0,
355
+ "LABEL_1": 1
356
+ },
357
+ "language_model_name_or_path": "bert-base-uncased",
358
+ "length_penalty": 1.0,
359
+ "local_loss": false,
360
+ "max_length": 20,
361
+ "max_text_len": 128,
362
+ "min_length": 0,
363
+ "mlp_dim": 3072,
364
+ "model_type": "m3d_clip",
365
+ "no_repeat_ngram_size": 0,
366
+ "num_beam_groups": 1,
367
+ "num_beams": 1,
368
+ "num_heads": 12,
369
+ "num_layers": 12,
370
+ "num_return_sequences": 1,
371
+ "output_attentions": false,
372
+ "output_hidden_states": false,
373
+ "output_scores": false,
374
+ "pad_token_id": null,
375
+ "patch_size": [
376
+ 4,
377
+ 16,
378
+ 16
379
+ ],
380
+ "pos_embed": "perceptron",
381
+ "prefix": null,
382
+ "problem_type": null,
383
+ "pruned_heads": {},
384
+ "remove_invalid_values": false,
385
+ "repetition_penalty": 1.0,
386
+ "return_dict": true,
387
+ "return_dict_in_generate": false,
388
+ "sep_token_id": null,
389
+ "spatial_dims": 3,
390
+ "suppress_tokens": null,
391
+ "task_specific_params": null,
392
+ "temperature": 1.0,
393
+ "tf_legacy_loss": false,
394
+ "tie_encoder_decoder": false,
395
+ "tie_word_embeddings": true,
396
+ "tokenizer_class": null,
397
+ "top_k": 50,
398
+ "top_p": 1.0,
399
+ "torch_dtype": "float32",
400
+ "torchscript": false,
401
+ "typical_p": 1.0,
402
+ "use_bfloat16": false,
403
+ "vocab_size": 30522
404
+ },
405
+ "vision3d_model_select_feature": "patch",
406
+ "vision3d_model_select_layer": -1,
407
+ "vision3d_model_type": "m3d"
408
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 768,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "right",
127
+ "sp_model_kwargs": {},
128
+ "spaces_between_special_tokens": false,
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff