hexuan21 commited on
Commit
fadfb56
1 Parent(s): 9567a5c

Training in progress, step 100

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 32002,
3
+ "<fake_token_around_image>": 32000,
4
+ "<image>": 32001
5
+ }
config.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TIGER-Lab/Mantis-8B-Idefics2",
3
+ "architectures": [
4
+ "Idefics2ForConditionalGeneration"
5
+ ],
6
+ "image_token_id": 32001,
7
+ "model_type": "idefics2",
8
+ "perceiver_config": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": false,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "silu",
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "min_length": 0,
42
+ "model_type": "idefics2",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_beam_groups": 1,
45
+ "num_beams": 1,
46
+ "num_key_value_heads": 4,
47
+ "num_return_sequences": 1,
48
+ "output_attentions": false,
49
+ "output_hidden_states": false,
50
+ "output_scores": false,
51
+ "pad_token_id": null,
52
+ "prefix": null,
53
+ "problem_type": null,
54
+ "pruned_heads": {},
55
+ "remove_invalid_values": false,
56
+ "repetition_penalty": 1.0,
57
+ "resampler_depth": 3,
58
+ "resampler_head_dim": 96,
59
+ "resampler_n_heads": 16,
60
+ "resampler_n_latents": 64,
61
+ "return_dict": true,
62
+ "return_dict_in_generate": false,
63
+ "sep_token_id": null,
64
+ "suppress_tokens": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "tf_legacy_loss": false,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": true,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torch_dtype": null,
74
+ "torchscript": false,
75
+ "typical_p": 1.0,
76
+ "use_bfloat16": false
77
+ },
78
+ "text_config": {
79
+ "_name_or_path": "",
80
+ "add_cross_attention": false,
81
+ "architectures": null,
82
+ "attention_dropout": 0.0,
83
+ "bad_words_ids": null,
84
+ "begin_suppress_tokens": null,
85
+ "bos_token_id": 1,
86
+ "chunk_size_feed_forward": 0,
87
+ "cross_attention_hidden_size": null,
88
+ "decoder_start_token_id": null,
89
+ "diversity_penalty": 0.0,
90
+ "do_sample": false,
91
+ "early_stopping": false,
92
+ "encoder_no_repeat_ngram_size": 0,
93
+ "eos_token_id": 2,
94
+ "exponential_decay_length_penalty": null,
95
+ "finetuning_task": null,
96
+ "forced_bos_token_id": null,
97
+ "forced_eos_token_id": null,
98
+ "hidden_act": "silu",
99
+ "hidden_size": 4096,
100
+ "id2label": {
101
+ "0": "LABEL_0",
102
+ "1": "LABEL_1"
103
+ },
104
+ "initializer_range": 0.02,
105
+ "intermediate_size": 14336,
106
+ "is_decoder": false,
107
+ "is_encoder_decoder": false,
108
+ "label2id": {
109
+ "LABEL_0": 0,
110
+ "LABEL_1": 1
111
+ },
112
+ "length_penalty": 1.0,
113
+ "max_length": 20,
114
+ "max_position_embeddings": 32768,
115
+ "min_length": 0,
116
+ "model_type": "mistral",
117
+ "no_repeat_ngram_size": 0,
118
+ "num_attention_heads": 32,
119
+ "num_beam_groups": 1,
120
+ "num_beams": 1,
121
+ "num_hidden_layers": 32,
122
+ "num_key_value_heads": 8,
123
+ "num_return_sequences": 1,
124
+ "output_attentions": false,
125
+ "output_hidden_states": false,
126
+ "output_scores": false,
127
+ "pad_token_id": 0,
128
+ "prefix": null,
129
+ "problem_type": null,
130
+ "pruned_heads": {},
131
+ "remove_invalid_values": false,
132
+ "repetition_penalty": 1.0,
133
+ "return_dict": true,
134
+ "return_dict_in_generate": false,
135
+ "rms_norm_eps": 1e-05,
136
+ "rope_theta": 10000.0,
137
+ "sep_token_id": null,
138
+ "sliding_window": 4096,
139
+ "suppress_tokens": null,
140
+ "task_specific_params": null,
141
+ "temperature": 1.0,
142
+ "tf_legacy_loss": false,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": false,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torch_dtype": null,
149
+ "torchscript": false,
150
+ "typical_p": 1.0,
151
+ "use_bfloat16": false,
152
+ "use_cache": true,
153
+ "vocab_size": 32003
154
+ },
155
+ "tie_word_embeddings": false,
156
+ "torch_dtype": "bfloat16",
157
+ "transformers_version": "4.41.1",
158
+ "use_cache": true,
159
+ "vision_config": {
160
+ "_name_or_path": "",
161
+ "add_cross_attention": false,
162
+ "architectures": null,
163
+ "attention_dropout": 0.0,
164
+ "bad_words_ids": null,
165
+ "begin_suppress_tokens": null,
166
+ "bos_token_id": null,
167
+ "chunk_size_feed_forward": 0,
168
+ "cross_attention_hidden_size": null,
169
+ "decoder_start_token_id": null,
170
+ "diversity_penalty": 0.0,
171
+ "do_sample": false,
172
+ "early_stopping": false,
173
+ "encoder_no_repeat_ngram_size": 0,
174
+ "eos_token_id": null,
175
+ "exponential_decay_length_penalty": null,
176
+ "finetuning_task": null,
177
+ "forced_bos_token_id": null,
178
+ "forced_eos_token_id": null,
179
+ "hidden_act": "gelu_pytorch_tanh",
180
+ "hidden_size": 1152,
181
+ "id2label": {
182
+ "0": "LABEL_0",
183
+ "1": "LABEL_1"
184
+ },
185
+ "image_size": 980,
186
+ "initializer_range": 0.02,
187
+ "intermediate_size": 4304,
188
+ "is_decoder": false,
189
+ "is_encoder_decoder": false,
190
+ "label2id": {
191
+ "LABEL_0": 0,
192
+ "LABEL_1": 1
193
+ },
194
+ "layer_norm_eps": 1e-06,
195
+ "length_penalty": 1.0,
196
+ "max_length": 20,
197
+ "min_length": 0,
198
+ "model_type": "idefics2",
199
+ "no_repeat_ngram_size": 0,
200
+ "num_attention_heads": 16,
201
+ "num_beam_groups": 1,
202
+ "num_beams": 1,
203
+ "num_channels": 3,
204
+ "num_hidden_layers": 27,
205
+ "num_return_sequences": 1,
206
+ "output_attentions": false,
207
+ "output_hidden_states": false,
208
+ "output_scores": false,
209
+ "pad_token_id": null,
210
+ "patch_size": 14,
211
+ "prefix": null,
212
+ "problem_type": null,
213
+ "pruned_heads": {},
214
+ "remove_invalid_values": false,
215
+ "repetition_penalty": 1.0,
216
+ "return_dict": true,
217
+ "return_dict_in_generate": false,
218
+ "sep_token_id": null,
219
+ "suppress_tokens": null,
220
+ "task_specific_params": null,
221
+ "temperature": 1.0,
222
+ "tf_legacy_loss": false,
223
+ "tie_encoder_decoder": false,
224
+ "tie_word_embeddings": true,
225
+ "tokenizer_class": null,
226
+ "top_k": 50,
227
+ "top_p": 1.0,
228
+ "torch_dtype": null,
229
+ "torchscript": false,
230
+ "typical_p": 1.0,
231
+ "use_bfloat16": false
232
+ }
233
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": false,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Idefics2ImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Idefics2Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 980,
24
+ "shortest_edge": 378
25
+ }
26
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_len": 64,
3
+ "processor_class": "Idefics2Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<fake_token_around_image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<image>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<end_of_utterance>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<unk>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<fake_token_around_image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<image>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<end_of_utterance>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<fake_token_around_image>",
56
+ "<image>",
57
+ "<end_of_utterance>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "clean_up_tokenization_spaces": false,
61
+ "do_image_splitting": false,
62
+ "eos_token": "</s>",
63
+ "legacy": false,
64
+ "model_max_length": 1000000000000000019884624838656,
65
+ "pad_token": "<unk>",
66
+ "processor_class": "Idefics2Processor",
67
+ "sp_model_kwargs": {},
68
+ "spaces_between_special_tokens": false,
69
+ "tokenizer_class": "LlamaTokenizer",
70
+ "unk_token": "<unk>",
71
+ "use_default_system_prompt": true
72
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36828bed4cd6f2048ee9aaee30a848e21b6253827ebf058237704768f40c52bc
3
+ size 6520