Commit
•
c5a0070
1
Parent(s):
a24b501
Update for `transformers` (#9)
Browse files- update (6bb7f577f7dbc16a282e0130daf68b0517af2a1c)
- add video index (4bd811a5739ae127c970cef373f083ae15507c4f)
- add pipeline (4b5bac732aca8c77b30351036d2d50d9865a8343)
Co-authored-by: Raushan Turganbay <RaushanTurganbay@users.noreply.huggingface.co>
- README.md +1 -1
- added_tokens.json +4 -0
- config.json +5 -202
- generation_config.json +8 -0
- model-00001-of-00002.safetensors +2 -2
- model.safetensors.index.json +0 -0
- processor_config.json +4 -0
- qformer_tokenizer/special_tokens_map.json +42 -6
- qformer_tokenizer/tokenizer_config.json +52 -0
- special_tokens_map.json +21 -3
- tokenizer.json +24 -3
- tokenizer_config.json +843 -0
README.md
CHANGED
@@ -4,7 +4,7 @@ license: mit
|
|
4 |
tags:
|
5 |
- vision
|
6 |
- image-captioning
|
7 |
-
pipeline_tag: image-to-text
|
8 |
---
|
9 |
|
10 |
# InstructBLIP model
|
|
|
4 |
tags:
|
5 |
- vision
|
6 |
- image-captioning
|
7 |
+
pipeline_tag: image-text-to-text
|
8 |
---
|
9 |
|
10 |
# InstructBLIP model
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image>": 32100,
|
3 |
+
"<video>": 32101
|
4 |
+
}
|
config.json
CHANGED
@@ -1,160 +1,45 @@
|
|
1 |
{
|
2 |
-
"_commit_hash": null,
|
3 |
"architectures": [
|
4 |
"InstructBlipForConditionalGeneration"
|
5 |
],
|
|
|
6 |
"initializer_factor": 1.0,
|
7 |
"initializer_range": 0.02,
|
8 |
"is_encoder_decoder": true,
|
9 |
"model_type": "instructblip",
|
10 |
"num_query_tokens": 32,
|
11 |
"qformer_config": {
|
12 |
-
"_name_or_path": "",
|
13 |
-
"add_cross_attention": false,
|
14 |
-
"architectures": null,
|
15 |
-
"attention_probs_dropout_prob": 0.1,
|
16 |
-
"bad_words_ids": null,
|
17 |
-
"begin_suppress_tokens": null,
|
18 |
-
"bos_token_id": null,
|
19 |
-
"chunk_size_feed_forward": 0,
|
20 |
"classifier_dropout": null,
|
21 |
-
"cross_attention_frequency": 2,
|
22 |
-
"cross_attention_hidden_size": null,
|
23 |
-
"decoder_start_token_id": null,
|
24 |
-
"diversity_penalty": 0.0,
|
25 |
-
"do_sample": false,
|
26 |
-
"early_stopping": false,
|
27 |
-
"encoder_hidden_size": 1408,
|
28 |
-
"encoder_no_repeat_ngram_size": 0,
|
29 |
-
"eos_token_id": null,
|
30 |
-
"exponential_decay_length_penalty": null,
|
31 |
-
"finetuning_task": null,
|
32 |
-
"forced_bos_token_id": null,
|
33 |
-
"forced_eos_token_id": null,
|
34 |
-
"hidden_act": "gelu",
|
35 |
-
"hidden_dropout_prob": 0.1,
|
36 |
-
"hidden_size": 768,
|
37 |
-
"id2label": {
|
38 |
-
"0": "LABEL_0",
|
39 |
-
"1": "LABEL_1"
|
40 |
-
},
|
41 |
-
"initializer_range": 0.02,
|
42 |
-
"intermediate_size": 3072,
|
43 |
-
"is_decoder": false,
|
44 |
-
"is_encoder_decoder": false,
|
45 |
-
"label2id": {
|
46 |
-
"LABEL_0": 0,
|
47 |
-
"LABEL_1": 1
|
48 |
-
},
|
49 |
-
"layer_norm_eps": 1e-12,
|
50 |
-
"length_penalty": 1.0,
|
51 |
-
"max_length": 20,
|
52 |
-
"max_position_embeddings": 512,
|
53 |
-
"min_length": 0,
|
54 |
"model_type": "instructblip_qformer",
|
55 |
-
"no_repeat_ngram_size": 0,
|
56 |
-
"num_attention_heads": 12,
|
57 |
-
"num_beam_groups": 1,
|
58 |
-
"num_beams": 1,
|
59 |
-
"num_hidden_layers": 12,
|
60 |
-
"num_return_sequences": 1,
|
61 |
-
"output_attentions": false,
|
62 |
-
"output_hidden_states": false,
|
63 |
-
"output_scores": false,
|
64 |
-
"pad_token_id": 0,
|
65 |
-
"position_embedding_type": "absolute",
|
66 |
-
"prefix": null,
|
67 |
-
"problem_type": null,
|
68 |
-
"pruned_heads": {},
|
69 |
-
"remove_invalid_values": false,
|
70 |
-
"repetition_penalty": 1.0,
|
71 |
-
"return_dict": true,
|
72 |
-
"return_dict_in_generate": false,
|
73 |
-
"sep_token_id": null,
|
74 |
-
"suppress_tokens": null,
|
75 |
-
"task_specific_params": null,
|
76 |
-
"temperature": 1.0,
|
77 |
-
"tf_legacy_loss": false,
|
78 |
-
"tie_encoder_decoder": false,
|
79 |
-
"tie_word_embeddings": true,
|
80 |
-
"tokenizer_class": null,
|
81 |
-
"top_k": 50,
|
82 |
-
"top_p": 1.0,
|
83 |
-
"torch_dtype": null,
|
84 |
-
"torchscript": false,
|
85 |
-
"transformers_version": "4.31.0.dev0",
|
86 |
-
"typical_p": 1.0,
|
87 |
-
"use_bfloat16": false,
|
88 |
"vocab_size": 30523
|
89 |
},
|
90 |
"text_config": {
|
91 |
-
"_name_or_path": "",
|
92 |
-
"add_cross_attention": false,
|
93 |
"architectures": [
|
94 |
"T5ForConditionalGeneration"
|
95 |
],
|
96 |
-
"bad_words_ids": null,
|
97 |
-
"begin_suppress_tokens": null,
|
98 |
"bos_token_id": 1,
|
99 |
-
"
|
100 |
-
"cross_attention_hidden_size": null,
|
101 |
"d_ff": 5120,
|
102 |
"d_kv": 64,
|
103 |
"d_model": 2048,
|
104 |
"decoder_start_token_id": 0,
|
105 |
"dense_act_fn": "gelu",
|
106 |
-
"diversity_penalty": 0.0,
|
107 |
-
"do_sample": false,
|
108 |
"dropout_rate": 0.1,
|
109 |
-
"early_stopping": false,
|
110 |
-
"encoder_no_repeat_ngram_size": 0,
|
111 |
"eos_token_id": 1,
|
112 |
-
"exponential_decay_length_penalty": null,
|
113 |
"feed_forward_proj": "gated-gelu",
|
114 |
-
"finetuning_task": null,
|
115 |
-
"forced_bos_token_id": null,
|
116 |
-
"forced_eos_token_id": null,
|
117 |
-
"id2label": {
|
118 |
-
"0": "LABEL_0",
|
119 |
-
"1": "LABEL_1"
|
120 |
-
},
|
121 |
"initializer_factor": 1.0,
|
122 |
-
"is_decoder": false,
|
123 |
"is_encoder_decoder": true,
|
124 |
"is_gated_act": true,
|
125 |
-
"label2id": {
|
126 |
-
"LABEL_0": 0,
|
127 |
-
"LABEL_1": 1
|
128 |
-
},
|
129 |
"layer_norm_epsilon": 1e-06,
|
130 |
-
"length_penalty": 1.0,
|
131 |
-
"max_length": 20,
|
132 |
-
"min_length": 0,
|
133 |
"model_type": "t5",
|
134 |
"n_positions": 512,
|
135 |
-
"no_repeat_ngram_size": 0,
|
136 |
-
"num_beam_groups": 1,
|
137 |
-
"num_beams": 1,
|
138 |
"num_decoder_layers": 24,
|
139 |
"num_heads": 32,
|
140 |
"num_layers": 24,
|
141 |
-
"num_return_sequences": 1,
|
142 |
-
"output_attentions": false,
|
143 |
-
"output_hidden_states": false,
|
144 |
"output_past": true,
|
145 |
-
"output_scores": false,
|
146 |
"pad_token_id": 0,
|
147 |
-
"prefix": null,
|
148 |
-
"problem_type": null,
|
149 |
-
"pruned_heads": {},
|
150 |
"relative_attention_max_distance": 128,
|
151 |
"relative_attention_num_buckets": 32,
|
152 |
-
"remove_invalid_values": false,
|
153 |
-
"repetition_penalty": 1.0,
|
154 |
-
"return_dict": true,
|
155 |
-
"return_dict_in_generate": false,
|
156 |
-
"sep_token_id": null,
|
157 |
-
"suppress_tokens": null,
|
158 |
"task_specific_params": {
|
159 |
"summarization": {
|
160 |
"early_stopping": true,
|
@@ -184,101 +69,19 @@
|
|
184 |
"prefix": "translate English to Romanian: "
|
185 |
}
|
186 |
},
|
187 |
-
"temperature": 1.0,
|
188 |
-
"tf_legacy_loss": false,
|
189 |
-
"tie_encoder_decoder": false,
|
190 |
"tie_word_embeddings": false,
|
191 |
-
"tokenizer_class": null,
|
192 |
-
"top_k": 50,
|
193 |
-
"top_p": 1.0,
|
194 |
"torch_dtype": "float32",
|
195 |
-
"torchscript": false,
|
196 |
-
"transformers_version": "4.31.0.dev0",
|
197 |
-
"typical_p": 1.0,
|
198 |
-
"use_bfloat16": false,
|
199 |
-
"use_cache": true,
|
200 |
"vocab_size": 32128
|
201 |
},
|
202 |
"tie_word_embeddings": false,
|
203 |
"torch_dtype": "float32",
|
204 |
-
"transformers_version":
|
205 |
"use_decoder_only_language_model": false,
|
|
|
206 |
"vision_config": {
|
207 |
-
"_name_or_path": "",
|
208 |
-
"add_cross_attention": false,
|
209 |
-
"architectures": null,
|
210 |
-
"attention_dropout": 0.0,
|
211 |
-
"bad_words_ids": null,
|
212 |
-
"begin_suppress_tokens": null,
|
213 |
-
"bos_token_id": null,
|
214 |
-
"chunk_size_feed_forward": 0,
|
215 |
-
"cross_attention_hidden_size": null,
|
216 |
-
"decoder_start_token_id": null,
|
217 |
-
"diversity_penalty": 0.0,
|
218 |
-
"do_sample": false,
|
219 |
"dropout": 0.0,
|
220 |
-
"early_stopping": false,
|
221 |
-
"encoder_no_repeat_ngram_size": 0,
|
222 |
-
"eos_token_id": null,
|
223 |
-
"exponential_decay_length_penalty": null,
|
224 |
-
"finetuning_task": null,
|
225 |
-
"forced_bos_token_id": null,
|
226 |
-
"forced_eos_token_id": null,
|
227 |
-
"hidden_act": "gelu",
|
228 |
-
"hidden_size": 1408,
|
229 |
-
"id2label": {
|
230 |
-
"0": "LABEL_0",
|
231 |
-
"1": "LABEL_1"
|
232 |
-
},
|
233 |
-
"image_size": 224,
|
234 |
"initializer_factor": 1.0,
|
235 |
-
"initializer_range": 1e-10,
|
236 |
-
"intermediate_size": 6144,
|
237 |
-
"is_decoder": false,
|
238 |
-
"is_encoder_decoder": false,
|
239 |
-
"label2id": {
|
240 |
-
"LABEL_0": 0,
|
241 |
-
"LABEL_1": 1
|
242 |
-
},
|
243 |
-
"layer_norm_eps": 1e-06,
|
244 |
-
"length_penalty": 1.0,
|
245 |
-
"max_length": 20,
|
246 |
-
"min_length": 0,
|
247 |
"model_type": "instructblip_vision_model",
|
248 |
-
"
|
249 |
-
"num_attention_heads": 16,
|
250 |
-
"num_beam_groups": 1,
|
251 |
-
"num_beams": 1,
|
252 |
-
"num_channels": 3,
|
253 |
-
"num_hidden_layers": 39,
|
254 |
-
"num_return_sequences": 1,
|
255 |
-
"output_attentions": false,
|
256 |
-
"output_hidden_states": false,
|
257 |
-
"output_scores": false,
|
258 |
-
"pad_token_id": null,
|
259 |
-
"patch_size": 14,
|
260 |
-
"prefix": null,
|
261 |
-
"problem_type": null,
|
262 |
-
"pruned_heads": {},
|
263 |
-
"qkv_bias": true,
|
264 |
-
"remove_invalid_values": false,
|
265 |
-
"repetition_penalty": 1.0,
|
266 |
-
"return_dict": true,
|
267 |
-
"return_dict_in_generate": false,
|
268 |
-
"sep_token_id": null,
|
269 |
-
"suppress_tokens": null,
|
270 |
-
"task_specific_params": null,
|
271 |
-
"temperature": 1.0,
|
272 |
-
"tf_legacy_loss": false,
|
273 |
-
"tie_encoder_decoder": false,
|
274 |
-
"tie_word_embeddings": true,
|
275 |
-
"tokenizer_class": null,
|
276 |
-
"top_k": 50,
|
277 |
-
"top_p": 1.0,
|
278 |
-
"torch_dtype": null,
|
279 |
-
"torchscript": false,
|
280 |
-
"transformers_version": "4.31.0.dev0",
|
281 |
-
"typical_p": 1.0,
|
282 |
-
"use_bfloat16": false
|
283 |
}
|
284 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"InstructBlipForConditionalGeneration"
|
4 |
],
|
5 |
+
"image_token_index": 32100,
|
6 |
"initializer_factor": 1.0,
|
7 |
"initializer_range": 0.02,
|
8 |
"is_encoder_decoder": true,
|
9 |
"model_type": "instructblip",
|
10 |
"num_query_tokens": 32,
|
11 |
"qformer_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"classifier_dropout": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"model_type": "instructblip_qformer",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"vocab_size": 30523
|
15 |
},
|
16 |
"text_config": {
|
|
|
|
|
17 |
"architectures": [
|
18 |
"T5ForConditionalGeneration"
|
19 |
],
|
|
|
|
|
20 |
"bos_token_id": 1,
|
21 |
+
"classifier_dropout": 0.0,
|
|
|
22 |
"d_ff": 5120,
|
23 |
"d_kv": 64,
|
24 |
"d_model": 2048,
|
25 |
"decoder_start_token_id": 0,
|
26 |
"dense_act_fn": "gelu",
|
|
|
|
|
27 |
"dropout_rate": 0.1,
|
|
|
|
|
28 |
"eos_token_id": 1,
|
|
|
29 |
"feed_forward_proj": "gated-gelu",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"initializer_factor": 1.0,
|
|
|
31 |
"is_encoder_decoder": true,
|
32 |
"is_gated_act": true,
|
|
|
|
|
|
|
|
|
33 |
"layer_norm_epsilon": 1e-06,
|
|
|
|
|
|
|
34 |
"model_type": "t5",
|
35 |
"n_positions": 512,
|
|
|
|
|
|
|
36 |
"num_decoder_layers": 24,
|
37 |
"num_heads": 32,
|
38 |
"num_layers": 24,
|
|
|
|
|
|
|
39 |
"output_past": true,
|
|
|
40 |
"pad_token_id": 0,
|
|
|
|
|
|
|
41 |
"relative_attention_max_distance": 128,
|
42 |
"relative_attention_num_buckets": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
"task_specific_params": {
|
44 |
"summarization": {
|
45 |
"early_stopping": true,
|
|
|
69 |
"prefix": "translate English to Romanian: "
|
70 |
}
|
71 |
},
|
|
|
|
|
|
|
72 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
73 |
"torch_dtype": "float32",
|
|
|
|
|
|
|
|
|
|
|
74 |
"vocab_size": 32128
|
75 |
},
|
76 |
"tie_word_embeddings": false,
|
77 |
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.47.0.dev0",
|
79 |
"use_decoder_only_language_model": false,
|
80 |
+
"video_token_index": 32101,
|
81 |
"vision_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
82 |
"dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
"initializer_factor": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
"model_type": "instructblip_vision_model",
|
85 |
+
"num_channels": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
}
|
87 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"decoder_start_token_id": 0,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.47.0.dev0"
|
8 |
+
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17cee128ee8cd7594fdbab95129819ea07997851a2426bd3ee0c24c4583d9054
|
3 |
+
size 9981400536
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
processor_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"num_query_tokens": 32,
|
3 |
+
"processor_class": "InstructBlipProcessor"
|
4 |
+
}
|
qformer_tokenizer/special_tokens_map.json
CHANGED
@@ -1,8 +1,44 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[DEC]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "[MASK]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "[PAD]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"sep_token": {
|
31 |
+
"content": "[SEP]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"unk_token": {
|
38 |
+
"content": "[UNK]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
}
|
44 |
}
|
qformer_tokenizer/tokenizer_config.json
CHANGED
@@ -1,7 +1,59 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": true,
|
|
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
"pad_token": "[PAD]",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"30522": {
|
44 |
+
"content": "[DEC]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"bos_token": "[DEC]",
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
"cls_token": "[CLS]",
|
55 |
"do_lower_case": true,
|
56 |
+
"extra_special_tokens": {},
|
57 |
"mask_token": "[MASK]",
|
58 |
"model_max_length": 512,
|
59 |
"pad_token": "[PAD]",
|
special_tokens_map.json
CHANGED
@@ -101,7 +101,25 @@
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
-
"eos_token":
|
105 |
-
|
106 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
}
|
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
+
"eos_token": {
|
105 |
+
"content": "</s>",
|
106 |
+
"lstrip": false,
|
107 |
+
"normalized": false,
|
108 |
+
"rstrip": false,
|
109 |
+
"single_word": false
|
110 |
+
},
|
111 |
+
"pad_token": {
|
112 |
+
"content": "<pad>",
|
113 |
+
"lstrip": false,
|
114 |
+
"normalized": false,
|
115 |
+
"rstrip": false,
|
116 |
+
"single_word": false
|
117 |
+
},
|
118 |
+
"unk_token": {
|
119 |
+
"content": "<unk>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false
|
124 |
+
}
|
125 |
}
|
tokenizer.json
CHANGED
@@ -929,6 +929,24 @@
|
|
929 |
"rstrip": false,
|
930 |
"normalized": false,
|
931 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
932 |
}
|
933 |
],
|
934 |
"normalizer": {
|
@@ -950,7 +968,8 @@
|
|
950 |
"pre_tokenizer": {
|
951 |
"type": "Metaspace",
|
952 |
"replacement": "▁",
|
953 |
-
"
|
|
|
954 |
},
|
955 |
"post_processor": {
|
956 |
"type": "TemplateProcessing",
|
@@ -1009,7 +1028,8 @@
|
|
1009 |
"decoder": {
|
1010 |
"type": "Metaspace",
|
1011 |
"replacement": "▁",
|
1012 |
-
"
|
|
|
1013 |
},
|
1014 |
"model": {
|
1015 |
"type": "Unigram",
|
@@ -129415,6 +129435,7 @@
|
|
129415 |
"<extra_id_0>",
|
129416 |
0.0
|
129417 |
]
|
129418 |
-
]
|
|
|
129419 |
}
|
129420 |
}
|
|
|
929 |
"rstrip": false,
|
930 |
"normalized": false,
|
931 |
"special": true
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"id": 32100,
|
935 |
+
"content": "<image>",
|
936 |
+
"single_word": false,
|
937 |
+
"lstrip": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"normalized": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"id": 32101,
|
944 |
+
"content": "<video>",
|
945 |
+
"single_word": false,
|
946 |
+
"lstrip": false,
|
947 |
+
"rstrip": false,
|
948 |
+
"normalized": false,
|
949 |
+
"special": true
|
950 |
}
|
951 |
],
|
952 |
"normalizer": {
|
|
|
968 |
"pre_tokenizer": {
|
969 |
"type": "Metaspace",
|
970 |
"replacement": "▁",
|
971 |
+
"prepend_scheme": "always",
|
972 |
+
"split": true
|
973 |
},
|
974 |
"post_processor": {
|
975 |
"type": "TemplateProcessing",
|
|
|
1028 |
"decoder": {
|
1029 |
"type": "Metaspace",
|
1030 |
"replacement": "▁",
|
1031 |
+
"prepend_scheme": "always",
|
1032 |
+
"split": true
|
1033 |
},
|
1034 |
"model": {
|
1035 |
"type": "Unigram",
|
|
|
129435 |
"<extra_id_0>",
|
129436 |
0.0
|
129437 |
]
|
129438 |
+
],
|
129439 |
+
"byte_fallback": false
|
129440 |
}
|
129441 |
}
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,846 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"<extra_id_0>",
|
4 |
"<extra_id_1>",
|
@@ -104,6 +946,7 @@
|
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
|
|
107 |
"model_max_length": 512,
|
108 |
"pad_token": "<pad>",
|
109 |
"processor_class": "InstructBlipProcessor",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<unk>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<extra_id_99>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "<extra_id_98>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32002": {
|
44 |
+
"content": "<extra_id_97>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"32003": {
|
52 |
+
"content": "<extra_id_96>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"32004": {
|
60 |
+
"content": "<extra_id_95>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"32005": {
|
68 |
+
"content": "<extra_id_94>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"32006": {
|
76 |
+
"content": "<extra_id_93>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"32007": {
|
84 |
+
"content": "<extra_id_92>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"32008": {
|
92 |
+
"content": "<extra_id_91>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"32009": {
|
100 |
+
"content": "<extra_id_90>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"32010": {
|
108 |
+
"content": "<extra_id_89>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"32011": {
|
116 |
+
"content": "<extra_id_88>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"32012": {
|
124 |
+
"content": "<extra_id_87>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"32013": {
|
132 |
+
"content": "<extra_id_86>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"32014": {
|
140 |
+
"content": "<extra_id_85>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"32015": {
|
148 |
+
"content": "<extra_id_84>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"32016": {
|
156 |
+
"content": "<extra_id_83>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"32017": {
|
164 |
+
"content": "<extra_id_82>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"32018": {
|
172 |
+
"content": "<extra_id_81>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"32019": {
|
180 |
+
"content": "<extra_id_80>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"32020": {
|
188 |
+
"content": "<extra_id_79>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"32021": {
|
196 |
+
"content": "<extra_id_78>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"32022": {
|
204 |
+
"content": "<extra_id_77>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"32023": {
|
212 |
+
"content": "<extra_id_76>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"32024": {
|
220 |
+
"content": "<extra_id_75>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"32025": {
|
228 |
+
"content": "<extra_id_74>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"32026": {
|
236 |
+
"content": "<extra_id_73>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"32027": {
|
244 |
+
"content": "<extra_id_72>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"32028": {
|
252 |
+
"content": "<extra_id_71>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"32029": {
|
260 |
+
"content": "<extra_id_70>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"32030": {
|
268 |
+
"content": "<extra_id_69>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"32031": {
|
276 |
+
"content": "<extra_id_68>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"32032": {
|
284 |
+
"content": "<extra_id_67>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"32033": {
|
292 |
+
"content": "<extra_id_66>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"32034": {
|
300 |
+
"content": "<extra_id_65>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"32035": {
|
308 |
+
"content": "<extra_id_64>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"32036": {
|
316 |
+
"content": "<extra_id_63>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"32037": {
|
324 |
+
"content": "<extra_id_62>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"32038": {
|
332 |
+
"content": "<extra_id_61>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"32039": {
|
340 |
+
"content": "<extra_id_60>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"32040": {
|
348 |
+
"content": "<extra_id_59>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"32041": {
|
356 |
+
"content": "<extra_id_58>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"32042": {
|
364 |
+
"content": "<extra_id_57>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"32043": {
|
372 |
+
"content": "<extra_id_56>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"32044": {
|
380 |
+
"content": "<extra_id_55>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"32045": {
|
388 |
+
"content": "<extra_id_54>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"32046": {
|
396 |
+
"content": "<extra_id_53>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"32047": {
|
404 |
+
"content": "<extra_id_52>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"32048": {
|
412 |
+
"content": "<extra_id_51>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"32049": {
|
420 |
+
"content": "<extra_id_50>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"32050": {
|
428 |
+
"content": "<extra_id_49>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"32051": {
|
436 |
+
"content": "<extra_id_48>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"32052": {
|
444 |
+
"content": "<extra_id_47>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"32053": {
|
452 |
+
"content": "<extra_id_46>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"32054": {
|
460 |
+
"content": "<extra_id_45>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"32055": {
|
468 |
+
"content": "<extra_id_44>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"32056": {
|
476 |
+
"content": "<extra_id_43>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"32057": {
|
484 |
+
"content": "<extra_id_42>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"32058": {
|
492 |
+
"content": "<extra_id_41>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"32059": {
|
500 |
+
"content": "<extra_id_40>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"32060": {
|
508 |
+
"content": "<extra_id_39>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"32061": {
|
516 |
+
"content": "<extra_id_38>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"32062": {
|
524 |
+
"content": "<extra_id_37>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"32063": {
|
532 |
+
"content": "<extra_id_36>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"32064": {
|
540 |
+
"content": "<extra_id_35>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"32065": {
|
548 |
+
"content": "<extra_id_34>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"32066": {
|
556 |
+
"content": "<extra_id_33>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"32067": {
|
564 |
+
"content": "<extra_id_32>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"32068": {
|
572 |
+
"content": "<extra_id_31>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"32069": {
|
580 |
+
"content": "<extra_id_30>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"32070": {
|
588 |
+
"content": "<extra_id_29>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"32071": {
|
596 |
+
"content": "<extra_id_28>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"32072": {
|
604 |
+
"content": "<extra_id_27>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"32073": {
|
612 |
+
"content": "<extra_id_26>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"32074": {
|
620 |
+
"content": "<extra_id_25>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"32075": {
|
628 |
+
"content": "<extra_id_24>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"32076": {
|
636 |
+
"content": "<extra_id_23>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"32077": {
|
644 |
+
"content": "<extra_id_22>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"32078": {
|
652 |
+
"content": "<extra_id_21>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"32079": {
|
660 |
+
"content": "<extra_id_20>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"32080": {
|
668 |
+
"content": "<extra_id_19>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"32081": {
|
676 |
+
"content": "<extra_id_18>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"32082": {
|
684 |
+
"content": "<extra_id_17>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"32083": {
|
692 |
+
"content": "<extra_id_16>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"32084": {
|
700 |
+
"content": "<extra_id_15>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"32085": {
|
708 |
+
"content": "<extra_id_14>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"32086": {
|
716 |
+
"content": "<extra_id_13>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"32087": {
|
724 |
+
"content": "<extra_id_12>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"32088": {
|
732 |
+
"content": "<extra_id_11>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"32089": {
|
740 |
+
"content": "<extra_id_10>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"32090": {
|
748 |
+
"content": "<extra_id_9>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"32091": {
|
756 |
+
"content": "<extra_id_8>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"32092": {
|
764 |
+
"content": "<extra_id_7>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"32093": {
|
772 |
+
"content": "<extra_id_6>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"32094": {
|
780 |
+
"content": "<extra_id_5>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"32095": {
|
788 |
+
"content": "<extra_id_4>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"32096": {
|
796 |
+
"content": "<extra_id_3>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"32097": {
|
804 |
+
"content": "<extra_id_2>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"32098": {
|
812 |
+
"content": "<extra_id_1>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"32099": {
|
820 |
+
"content": "<extra_id_0>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"32100": {
|
828 |
+
"content": "<image>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"32101": {
|
836 |
+
"content": "<video>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
}
|
843 |
+
},
|
844 |
"additional_special_tokens": [
|
845 |
"<extra_id_0>",
|
846 |
"<extra_id_1>",
|
|
|
946 |
"clean_up_tokenization_spaces": true,
|
947 |
"eos_token": "</s>",
|
948 |
"extra_ids": 100,
|
949 |
+
"extra_special_tokens": {},
|
950 |
"model_max_length": 512,
|
951 |
"pad_token": "<pad>",
|
952 |
"processor_class": "InstructBlipProcessor",
|