Commit
•
cc1362c
1
Parent(s):
164da4f
Update for `transformers` changes (#5)
Browse files- update (8ecee597dccd0f8ee2e0c4e057109f85ad7b4b1e)
- add video index (c2ef27c0dcfaf3b06114e31c0f7bdeae6695e2a1)
- add pipeline (3f553d44d832eb790714955f131f7c76f2288098)
Co-authored-by: Raushan Turganbay <RaushanTurganbay@users.noreply.huggingface.co>
- README.md +1 -1
- added_tokens.json +2 -0
- config.json +12 -207
- generation_config.json +7 -0
- model-00001-of-00006.safetensors +2 -2
- model-00002-of-00006.safetensors +2 -2
- model-00003-of-00006.safetensors +2 -2
- model-00004-of-00006.safetensors +2 -2
- model-00005-of-00006.safetensors +2 -2
- model-00006-of-00006.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 +0 -0
- tokenizer_config.json +59 -10
README.md
CHANGED
@@ -4,7 +4,7 @@ license: other
|
|
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
CHANGED
@@ -1,3 +1,5 @@
|
|
1 |
{
|
|
|
|
|
2 |
"[PAD]": 32000
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"<image>": 32001,
|
3 |
+
"<video>": 32002,
|
4 |
"[PAD]": 32000
|
5 |
}
|
config.json
CHANGED
@@ -1,244 +1,49 @@
|
|
1 |
{
|
2 |
-
"_commit_hash": null,
|
3 |
"architectures": [
|
4 |
"InstructBlipForConditionalGeneration"
|
5 |
],
|
|
|
6 |
"initializer_factor": 1.0,
|
7 |
"initializer_range": 0.02,
|
8 |
"model_type": "instructblip",
|
9 |
"num_query_tokens": 32,
|
10 |
"qformer_config": {
|
11 |
-
"_name_or_path": "",
|
12 |
-
"add_cross_attention": false,
|
13 |
-
"architectures": null,
|
14 |
-
"attention_probs_dropout_prob": 0.1,
|
15 |
-
"bad_words_ids": null,
|
16 |
-
"begin_suppress_tokens": null,
|
17 |
-
"bos_token_id": null,
|
18 |
-
"chunk_size_feed_forward": 0,
|
19 |
-
"cross_attention_frequency": 2,
|
20 |
-
"cross_attention_hidden_size": null,
|
21 |
-
"decoder_start_token_id": null,
|
22 |
-
"diversity_penalty": 0.0,
|
23 |
-
"do_sample": false,
|
24 |
-
"early_stopping": false,
|
25 |
-
"encoder_hidden_size": 1408,
|
26 |
-
"encoder_no_repeat_ngram_size": 0,
|
27 |
-
"eos_token_id": null,
|
28 |
-
"exponential_decay_length_penalty": null,
|
29 |
-
"finetuning_task": null,
|
30 |
-
"forced_bos_token_id": null,
|
31 |
-
"forced_eos_token_id": null,
|
32 |
-
"hidden_act": "gelu",
|
33 |
-
"hidden_dropout_prob": 0.1,
|
34 |
-
"hidden_size": 768,
|
35 |
-
"id2label": {
|
36 |
-
"0": "LABEL_0",
|
37 |
-
"1": "LABEL_1"
|
38 |
-
},
|
39 |
-
"initializer_range": 0.02,
|
40 |
-
"intermediate_size": 3072,
|
41 |
-
"is_decoder": false,
|
42 |
-
"is_encoder_decoder": false,
|
43 |
-
"label2id": {
|
44 |
-
"LABEL_0": 0,
|
45 |
-
"LABEL_1": 1
|
46 |
-
},
|
47 |
-
"layer_norm_eps": 1e-12,
|
48 |
-
"length_penalty": 1.0,
|
49 |
-
"max_length": 20,
|
50 |
-
"max_position_embeddings": 512,
|
51 |
-
"min_length": 0,
|
52 |
"model_type": "instructblip_qformer",
|
53 |
-
"no_repeat_ngram_size": 0,
|
54 |
-
"num_attention_heads": 12,
|
55 |
-
"num_beam_groups": 1,
|
56 |
-
"num_beams": 1,
|
57 |
-
"num_hidden_layers": 12,
|
58 |
-
"num_return_sequences": 1,
|
59 |
-
"output_attentions": false,
|
60 |
-
"output_hidden_states": false,
|
61 |
-
"output_scores": false,
|
62 |
-
"pad_token_id": 0,
|
63 |
-
"position_embedding_type": "absolute",
|
64 |
-
"prefix": null,
|
65 |
-
"problem_type": null,
|
66 |
-
"pruned_heads": {},
|
67 |
-
"remove_invalid_values": false,
|
68 |
-
"repetition_penalty": 1.0,
|
69 |
-
"return_dict": true,
|
70 |
-
"return_dict_in_generate": false,
|
71 |
-
"sep_token_id": null,
|
72 |
-
"suppress_tokens": null,
|
73 |
-
"task_specific_params": null,
|
74 |
-
"temperature": 1.0,
|
75 |
-
"tf_legacy_loss": false,
|
76 |
-
"tie_encoder_decoder": false,
|
77 |
-
"tie_word_embeddings": true,
|
78 |
-
"tokenizer_class": null,
|
79 |
-
"top_k": 50,
|
80 |
-
"top_p": 1.0,
|
81 |
-
"torch_dtype": null,
|
82 |
-
"torchscript": false,
|
83 |
-
"transformers_version": "4.31.0.dev0",
|
84 |
-
"typical_p": 1.0,
|
85 |
-
"use_bfloat16": false,
|
86 |
"vocab_size": 30523
|
87 |
},
|
88 |
"text_config": {
|
89 |
-
"_name_or_path": "",
|
90 |
-
"add_cross_attention": false,
|
91 |
"architectures": [
|
92 |
"LLaMAForCausalLM"
|
93 |
],
|
94 |
-
"
|
95 |
-
"begin_suppress_tokens": null,
|
96 |
"bos_token_id": 0,
|
97 |
-
"chunk_size_feed_forward": 0,
|
98 |
-
"cross_attention_hidden_size": null,
|
99 |
-
"decoder_start_token_id": null,
|
100 |
-
"diversity_penalty": 0.0,
|
101 |
-
"do_sample": false,
|
102 |
-
"early_stopping": false,
|
103 |
-
"encoder_no_repeat_ngram_size": 0,
|
104 |
"eos_token_id": 1,
|
105 |
-
"
|
106 |
-
"finetuning_task": null,
|
107 |
-
"forced_bos_token_id": null,
|
108 |
-
"forced_eos_token_id": null,
|
109 |
"hidden_act": "silu",
|
110 |
"hidden_size": 5120,
|
111 |
-
"id2label": {
|
112 |
-
"0": "LABEL_0",
|
113 |
-
"1": "LABEL_1"
|
114 |
-
},
|
115 |
"initializer_range": 0.02,
|
116 |
"intermediate_size": 13824,
|
117 |
-
"is_decoder": false,
|
118 |
-
"is_encoder_decoder": false,
|
119 |
-
"label2id": {
|
120 |
-
"LABEL_0": 0,
|
121 |
-
"LABEL_1": 1
|
122 |
-
},
|
123 |
-
"length_penalty": 1.0,
|
124 |
-
"max_length": 20,
|
125 |
-
"max_position_embeddings": 2048,
|
126 |
"max_sequence_length": 2048,
|
127 |
-
"
|
128 |
"model_type": "llama",
|
129 |
-
"no_repeat_ngram_size": 0,
|
130 |
"num_attention_heads": 40,
|
131 |
-
"num_beam_groups": 1,
|
132 |
-
"num_beams": 1,
|
133 |
"num_hidden_layers": 40,
|
134 |
-
"
|
135 |
-
"output_attentions": false,
|
136 |
-
"output_hidden_states": false,
|
137 |
-
"output_scores": false,
|
138 |
"pad_token_id": 32000,
|
139 |
-
"
|
140 |
-
"problem_type": null,
|
141 |
-
"pruned_heads": {},
|
142 |
-
"remove_invalid_values": false,
|
143 |
-
"repetition_penalty": 1.0,
|
144 |
-
"return_dict": true,
|
145 |
-
"return_dict_in_generate": false,
|
146 |
"rms_norm_eps": 1e-06,
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"task_specific_params": null,
|
150 |
-
"temperature": 1.0,
|
151 |
-
"tf_legacy_loss": false,
|
152 |
-
"tie_encoder_decoder": false,
|
153 |
"tie_word_embeddings": false,
|
154 |
-
"tokenizer_class": null,
|
155 |
-
"top_k": 50,
|
156 |
-
"top_p": 1.0,
|
157 |
"torch_dtype": "float16",
|
158 |
-
"
|
159 |
-
"transformers_version": "4.31.0.dev0",
|
160 |
-
"typical_p": 1.0,
|
161 |
-
"use_bfloat16": false,
|
162 |
-
"use_cache": true,
|
163 |
-
"vocab_size": 32001
|
164 |
},
|
165 |
"tie_word_embeddings": false,
|
166 |
"torch_dtype": "float32",
|
167 |
-
"transformers_version":
|
168 |
"use_decoder_only_language_model": true,
|
|
|
169 |
"vision_config": {
|
170 |
-
"
|
171 |
-
"add_cross_attention": false,
|
172 |
-
"architectures": null,
|
173 |
-
"attention_dropout": 0.0,
|
174 |
-
"bad_words_ids": null,
|
175 |
-
"begin_suppress_tokens": null,
|
176 |
-
"bos_token_id": null,
|
177 |
-
"chunk_size_feed_forward": 0,
|
178 |
-
"cross_attention_hidden_size": null,
|
179 |
-
"decoder_start_token_id": null,
|
180 |
-
"diversity_penalty": 0.0,
|
181 |
-
"do_sample": false,
|
182 |
-
"early_stopping": false,
|
183 |
-
"encoder_no_repeat_ngram_size": 0,
|
184 |
-
"eos_token_id": null,
|
185 |
-
"exponential_decay_length_penalty": null,
|
186 |
-
"finetuning_task": null,
|
187 |
-
"forced_bos_token_id": null,
|
188 |
-
"forced_eos_token_id": null,
|
189 |
-
"hidden_act": "gelu",
|
190 |
-
"hidden_size": 1408,
|
191 |
-
"id2label": {
|
192 |
-
"0": "LABEL_0",
|
193 |
-
"1": "LABEL_1"
|
194 |
-
},
|
195 |
-
"image_size": 224,
|
196 |
-
"initializer_range": 1e-10,
|
197 |
-
"intermediate_size": 6144,
|
198 |
-
"is_decoder": false,
|
199 |
-
"is_encoder_decoder": false,
|
200 |
-
"label2id": {
|
201 |
-
"LABEL_0": 0,
|
202 |
-
"LABEL_1": 1
|
203 |
-
},
|
204 |
-
"layer_norm_eps": 1e-06,
|
205 |
-
"length_penalty": 1.0,
|
206 |
-
"max_length": 20,
|
207 |
-
"min_length": 0,
|
208 |
-
"model_type": "instructblip_vision_model",
|
209 |
-
"no_repeat_ngram_size": 0,
|
210 |
-
"num_attention_heads": 16,
|
211 |
-
"num_beam_groups": 1,
|
212 |
-
"num_beams": 1,
|
213 |
-
"num_hidden_layers": 39,
|
214 |
-
"num_return_sequences": 1,
|
215 |
-
"output_attentions": false,
|
216 |
-
"output_hidden_states": false,
|
217 |
-
"output_scores": false,
|
218 |
-
"pad_token_id": null,
|
219 |
-
"patch_size": 14,
|
220 |
-
"prefix": null,
|
221 |
-
"problem_type": null,
|
222 |
-
"pruned_heads": {},
|
223 |
-
"qkv_bias": true,
|
224 |
-
"remove_invalid_values": false,
|
225 |
-
"repetition_penalty": 1.0,
|
226 |
-
"return_dict": true,
|
227 |
-
"return_dict_in_generate": false,
|
228 |
-
"sep_token_id": null,
|
229 |
-
"suppress_tokens": null,
|
230 |
-
"task_specific_params": null,
|
231 |
-
"temperature": 1.0,
|
232 |
-
"tf_legacy_loss": false,
|
233 |
-
"tie_encoder_decoder": false,
|
234 |
-
"tie_word_embeddings": true,
|
235 |
-
"tokenizer_class": null,
|
236 |
-
"top_k": 50,
|
237 |
-
"top_p": 1.0,
|
238 |
-
"torch_dtype": null,
|
239 |
-
"torchscript": false,
|
240 |
-
"transformers_version": "4.31.0.dev0",
|
241 |
-
"typical_p": 1.0,
|
242 |
-
"use_bfloat16": false
|
243 |
}
|
244 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"InstructBlipForConditionalGeneration"
|
4 |
],
|
5 |
+
"image_token_index": 32001,
|
6 |
"initializer_factor": 1.0,
|
7 |
"initializer_range": 0.02,
|
8 |
"model_type": "instructblip",
|
9 |
"num_query_tokens": 32,
|
10 |
"qformer_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"model_type": "instructblip_qformer",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"vocab_size": 30523
|
13 |
},
|
14 |
"text_config": {
|
|
|
|
|
15 |
"architectures": [
|
16 |
"LLaMAForCausalLM"
|
17 |
],
|
18 |
+
"attention_bias": false,
|
|
|
19 |
"bos_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"eos_token_id": 1,
|
21 |
+
"head_dim": 128,
|
|
|
|
|
|
|
22 |
"hidden_act": "silu",
|
23 |
"hidden_size": 5120,
|
|
|
|
|
|
|
|
|
24 |
"initializer_range": 0.02,
|
25 |
"intermediate_size": 13824,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"max_sequence_length": 2048,
|
27 |
+
"mlp_bias": false,
|
28 |
"model_type": "llama",
|
|
|
29 |
"num_attention_heads": 40,
|
|
|
|
|
30 |
"num_hidden_layers": 40,
|
31 |
+
"num_key_value_heads": 40,
|
|
|
|
|
|
|
32 |
"pad_token_id": 32000,
|
33 |
+
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"rms_norm_eps": 1e-06,
|
35 |
+
"rope_scaling": null,
|
36 |
+
"rope_theta": 10000.0,
|
|
|
|
|
|
|
|
|
37 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
38 |
"torch_dtype": "float16",
|
39 |
+
"vocab_size": 32064
|
|
|
|
|
|
|
|
|
|
|
40 |
},
|
41 |
"tie_word_embeddings": false,
|
42 |
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.47.0.dev0",
|
44 |
"use_decoder_only_language_model": true,
|
45 |
+
"video_token_index": 32002,
|
46 |
"vision_config": {
|
47 |
+
"model_type": "instructblip_vision_model"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 32000,
|
6 |
+
"transformers_version": "4.47.0.dev0"
|
7 |
+
}
|
model-00001-of-00006.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 sha256:428b0d5ca487f34d774946392802451e88691722fd942e73b1b6f0938de71cba
|
3 |
+
size 9868071712
|
model-00002-of-00006.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 sha256:87f01b7cee567a2b709c7d7d543fdaafcf2c9fa62a7f3483dc11d7df8cef3304
|
3 |
+
size 9867437080
|
model-00003-of-00006.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:b0db3116a9d7772293d490edcda023fde18d5d05c23e986c7cb5b90f4c97a7ff
|
3 |
+
size 9940837328
|
model-00004-of-00006.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 sha256:1cbda65d83efac99725d0b9711ef266d56bfa71ad60dbbca4bcd3fd1aa4901dc
|
3 |
+
size 9940837328
|
model-00005-of-00006.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 sha256:9b770fa3b52491d50b123fefba46f03495e4055b93e018f1c55bac3bf06646a3
|
3 |
+
size 9867395920
|
model-00006-of-00006.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 sha256:78e6f106ac84f3dfb2ce0c1efc59fe8436ab9d85dcd306c8d0e46e7b8839dcda
|
3 |
+
size 7283943792
|
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
@@ -1,5 +1,11 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"eos_token": {
|
4 |
"content": "</s>",
|
5 |
"lstrip": false,
|
@@ -7,6 +13,18 @@
|
|
7 |
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
10 |
-
"pad_token":
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"eos_token": {
|
10 |
"content": "</s>",
|
11 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "</s>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,19 +1,68 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "</s>",
|
3 |
"clean_up_tokenization_spaces": false,
|
4 |
-
"eos_token":
|
5 |
-
|
6 |
-
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": true,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
"model_max_length": 2048,
|
13 |
-
"pad_token":
|
14 |
"processor_class": "InstructBlipProcessor",
|
15 |
"sp_model_kwargs": {},
|
16 |
"tokenizer_class": "LlamaTokenizer",
|
17 |
"truncation_side": "left",
|
18 |
-
"unk_token": "</s>"
|
|
|
19 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<image>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<video>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
}
|
54 |
+
},
|
55 |
"bos_token": "</s>",
|
56 |
"clean_up_tokenization_spaces": false,
|
57 |
+
"eos_token": "</s>",
|
58 |
+
"extra_special_tokens": {},
|
59 |
+
"legacy": true,
|
|
|
|
|
|
|
|
|
|
|
60 |
"model_max_length": 2048,
|
61 |
+
"pad_token": "[PAD]",
|
62 |
"processor_class": "InstructBlipProcessor",
|
63 |
"sp_model_kwargs": {},
|
64 |
"tokenizer_class": "LlamaTokenizer",
|
65 |
"truncation_side": "left",
|
66 |
+
"unk_token": "</s>",
|
67 |
+
"use_default_system_prompt": false
|
68 |
}
|