upload initial
Browse files- README.md +148 -0
- config.json +170 -0
- handler.py +59 -0
- preprocessor_config.json +25 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: image-to-text
|
3 |
+
tags:
|
4 |
+
- image-captioning
|
5 |
+
languages:
|
6 |
+
- en
|
7 |
+
license: bsd-3-clause
|
8 |
+
---
|
9 |
+
|
10 |
+
# BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
|
11 |
+
|
12 |
+
Model card for image captioning pretrained on COCO dataset - base architecture (with ViT large backbone).
|
13 |
+
|
14 |
+
| ![BLIP.gif](https://cdn-uploads.huggingface.co/production/uploads/1670928184033-62441d1d9fdefb55a0b7d12c.gif) |
|
15 |
+
|:--:|
|
16 |
+
| <b> Pull figure from BLIP official repo | Image source: https://github.com/salesforce/BLIP </b>|
|
17 |
+
|
18 |
+
## TL;DR
|
19 |
+
|
20 |
+
Authors from the [paper](https://arxiv.org/abs/2201.12086) write in the abstract:
|
21 |
+
|
22 |
+
*Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state-of-the-art results on a wide range of vision-language tasks, such as image-text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to videolanguage tasks in a zero-shot manner. Code, models, and datasets are released.*
|
23 |
+
|
24 |
+
## Usage
|
25 |
+
|
26 |
+
You can use this model for conditional and un-conditional image captioning
|
27 |
+
|
28 |
+
### Using the Pytorch model
|
29 |
+
|
30 |
+
#### Running the model on CPU
|
31 |
+
|
32 |
+
<details>
|
33 |
+
<summary> Click to expand </summary>
|
34 |
+
|
35 |
+
```python
|
36 |
+
import requests
|
37 |
+
from PIL import Image
|
38 |
+
from transformers import BlipProcessor, BlipForConditionalGeneration
|
39 |
+
|
40 |
+
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
|
41 |
+
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
|
42 |
+
|
43 |
+
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
|
44 |
+
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
|
45 |
+
|
46 |
+
# conditional image captioning
|
47 |
+
text = "a photography of"
|
48 |
+
inputs = processor(raw_image, text, return_tensors="pt")
|
49 |
+
|
50 |
+
out = model.generate(**inputs)
|
51 |
+
print(processor.decode(out[0], skip_special_tokens=True))
|
52 |
+
|
53 |
+
# unconditional image captioning
|
54 |
+
inputs = processor(raw_image, return_tensors="pt")
|
55 |
+
|
56 |
+
out = model.generate(**inputs)
|
57 |
+
print(processor.decode(out[0], skip_special_tokens=True))
|
58 |
+
```
|
59 |
+
</details>
|
60 |
+
|
61 |
+
#### Running the model on GPU
|
62 |
+
|
63 |
+
##### In full precision
|
64 |
+
|
65 |
+
<details>
|
66 |
+
<summary> Click to expand </summary>
|
67 |
+
|
68 |
+
```python
|
69 |
+
import requests
|
70 |
+
from PIL import Image
|
71 |
+
from transformers import BlipProcessor, BlipForConditionalGeneration
|
72 |
+
|
73 |
+
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
|
74 |
+
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").to("cuda")
|
75 |
+
|
76 |
+
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
|
77 |
+
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
|
78 |
+
|
79 |
+
# conditional image captioning
|
80 |
+
text = "a photography of"
|
81 |
+
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
|
82 |
+
|
83 |
+
out = model.generate(**inputs)
|
84 |
+
print(processor.decode(out[0], skip_special_tokens=True))
|
85 |
+
|
86 |
+
# unconditional image captioning
|
87 |
+
inputs = processor(raw_image, return_tensors="pt").to("cuda")
|
88 |
+
|
89 |
+
out = model.generate(**inputs)
|
90 |
+
print(processor.decode(out[0], skip_special_tokens=True))
|
91 |
+
```
|
92 |
+
</details>
|
93 |
+
|
94 |
+
##### In half precision (`float16`)
|
95 |
+
|
96 |
+
<details>
|
97 |
+
<summary> Click to expand </summary>
|
98 |
+
|
99 |
+
```python
|
100 |
+
import torch
|
101 |
+
import requests
|
102 |
+
from PIL import Image
|
103 |
+
from transformers import BlipProcessor, BlipForConditionalGeneration
|
104 |
+
|
105 |
+
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
|
106 |
+
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", torch_dtype=torch.float16).to("cuda")
|
107 |
+
|
108 |
+
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
|
109 |
+
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
|
110 |
+
|
111 |
+
# conditional image captioning
|
112 |
+
text = "a photography of"
|
113 |
+
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
|
114 |
+
|
115 |
+
out = model.generate(**inputs)
|
116 |
+
print(processor.decode(out[0], skip_special_tokens=True))
|
117 |
+
# >>> a photography of a woman and her dog
|
118 |
+
|
119 |
+
# unconditional image captioning
|
120 |
+
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
|
121 |
+
|
122 |
+
out = model.generate(**inputs)
|
123 |
+
print(processor.decode(out[0], skip_special_tokens=True))
|
124 |
+
>>> a woman sitting on the beach with her dog
|
125 |
+
```
|
126 |
+
</details>
|
127 |
+
|
128 |
+
## BibTex and citation info
|
129 |
+
|
130 |
+
```
|
131 |
+
@misc{https://doi.org/10.48550/arxiv.2201.12086,
|
132 |
+
doi = {10.48550/ARXIV.2201.12086},
|
133 |
+
|
134 |
+
url = {https://arxiv.org/abs/2201.12086},
|
135 |
+
|
136 |
+
author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
|
137 |
+
|
138 |
+
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
139 |
+
|
140 |
+
title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
|
141 |
+
|
142 |
+
publisher = {arXiv},
|
143 |
+
|
144 |
+
year = {2022},
|
145 |
+
|
146 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
147 |
+
}
|
148 |
+
```
|
config.json
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": null,
|
3 |
+
"architectures": [
|
4 |
+
"BlipForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"image_text_hidden_size": 256,
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"logit_scale_init_value": 2.6592,
|
9 |
+
"model_type": "blip",
|
10 |
+
"projection_dim": 512,
|
11 |
+
"text_config": {
|
12 |
+
"_name_or_path": "",
|
13 |
+
"add_cross_attention": false,
|
14 |
+
"architectures": null,
|
15 |
+
"attention_probs_dropout_prob": 0.0,
|
16 |
+
"bad_words_ids": null,
|
17 |
+
"begin_suppress_tokens": null,
|
18 |
+
"bos_token_id": 30522,
|
19 |
+
"chunk_size_feed_forward": 0,
|
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": 1024,
|
26 |
+
"encoder_no_repeat_ngram_size": 0,
|
27 |
+
"eos_token_id": 2,
|
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": 0.0,
|
34 |
+
"hidden_size": 768,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1"
|
38 |
+
},
|
39 |
+
"initializer_factor": 1.0,
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"is_decoder": true,
|
43 |
+
"is_encoder_decoder": false,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1
|
47 |
+
},
|
48 |
+
"layer_norm_eps": 1e-12,
|
49 |
+
"length_penalty": 1.0,
|
50 |
+
"max_length": 20,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"min_length": 0,
|
53 |
+
"model_type": "blip_text_model",
|
54 |
+
"no_repeat_ngram_size": 0,
|
55 |
+
"num_attention_heads": 12,
|
56 |
+
"num_beam_groups": 1,
|
57 |
+
"num_beams": 1,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"num_return_sequences": 1,
|
60 |
+
"output_attentions": false,
|
61 |
+
"output_hidden_states": false,
|
62 |
+
"output_scores": false,
|
63 |
+
"pad_token_id": 0,
|
64 |
+
"prefix": null,
|
65 |
+
"problem_type": null,
|
66 |
+
"projection_dim": 768,
|
67 |
+
"pruned_heads": {},
|
68 |
+
"remove_invalid_values": false,
|
69 |
+
"repetition_penalty": 1.0,
|
70 |
+
"return_dict": true,
|
71 |
+
"return_dict_in_generate": false,
|
72 |
+
"sep_token_id": 102,
|
73 |
+
"suppress_tokens": null,
|
74 |
+
"task_specific_params": null,
|
75 |
+
"temperature": 1.0,
|
76 |
+
"tf_legacy_loss": false,
|
77 |
+
"tie_encoder_decoder": false,
|
78 |
+
"tie_word_embeddings": true,
|
79 |
+
"tokenizer_class": null,
|
80 |
+
"top_k": 50,
|
81 |
+
"top_p": 1.0,
|
82 |
+
"torch_dtype": null,
|
83 |
+
"torchscript": false,
|
84 |
+
"transformers_version": "4.26.0.dev0",
|
85 |
+
"typical_p": 1.0,
|
86 |
+
"use_bfloat16": false,
|
87 |
+
"use_cache": true,
|
88 |
+
"vocab_size": 30524
|
89 |
+
},
|
90 |
+
"torch_dtype": "float32",
|
91 |
+
"transformers_version": null,
|
92 |
+
"vision_config": {
|
93 |
+
"_name_or_path": "",
|
94 |
+
"add_cross_attention": false,
|
95 |
+
"architectures": null,
|
96 |
+
"attention_dropout": 0.0,
|
97 |
+
"bad_words_ids": null,
|
98 |
+
"begin_suppress_tokens": null,
|
99 |
+
"bos_token_id": null,
|
100 |
+
"chunk_size_feed_forward": 0,
|
101 |
+
"cross_attention_hidden_size": null,
|
102 |
+
"decoder_start_token_id": null,
|
103 |
+
"diversity_penalty": 0.0,
|
104 |
+
"do_sample": false,
|
105 |
+
"dropout": 0.0,
|
106 |
+
"early_stopping": false,
|
107 |
+
"encoder_no_repeat_ngram_size": 0,
|
108 |
+
"eos_token_id": null,
|
109 |
+
"exponential_decay_length_penalty": null,
|
110 |
+
"finetuning_task": null,
|
111 |
+
"forced_bos_token_id": null,
|
112 |
+
"forced_eos_token_id": null,
|
113 |
+
"hidden_act": "gelu",
|
114 |
+
"hidden_size": 1024,
|
115 |
+
"id2label": {
|
116 |
+
"0": "LABEL_0",
|
117 |
+
"1": "LABEL_1"
|
118 |
+
},
|
119 |
+
"image_size": 384,
|
120 |
+
"initializer_factor": 1.0,
|
121 |
+
"initializer_range": 0.02,
|
122 |
+
"intermediate_size": 4096,
|
123 |
+
"is_decoder": false,
|
124 |
+
"is_encoder_decoder": false,
|
125 |
+
"label2id": {
|
126 |
+
"LABEL_0": 0,
|
127 |
+
"LABEL_1": 1
|
128 |
+
},
|
129 |
+
"layer_norm_eps": 1e-05,
|
130 |
+
"length_penalty": 1.0,
|
131 |
+
"max_length": 20,
|
132 |
+
"min_length": 0,
|
133 |
+
"model_type": "blip_vision_model",
|
134 |
+
"no_repeat_ngram_size": 0,
|
135 |
+
"num_attention_heads": 16,
|
136 |
+
"num_beam_groups": 1,
|
137 |
+
"num_beams": 1,
|
138 |
+
"num_channels": 3,
|
139 |
+
"num_hidden_layers": 24,
|
140 |
+
"num_return_sequences": 1,
|
141 |
+
"output_attentions": false,
|
142 |
+
"output_hidden_states": false,
|
143 |
+
"output_scores": false,
|
144 |
+
"pad_token_id": null,
|
145 |
+
"patch_size": 16,
|
146 |
+
"prefix": null,
|
147 |
+
"problem_type": null,
|
148 |
+
"projection_dim": 512,
|
149 |
+
"pruned_heads": {},
|
150 |
+
"remove_invalid_values": false,
|
151 |
+
"repetition_penalty": 1.0,
|
152 |
+
"return_dict": true,
|
153 |
+
"return_dict_in_generate": false,
|
154 |
+
"sep_token_id": null,
|
155 |
+
"suppress_tokens": null,
|
156 |
+
"task_specific_params": null,
|
157 |
+
"temperature": 1.0,
|
158 |
+
"tf_legacy_loss": false,
|
159 |
+
"tie_encoder_decoder": false,
|
160 |
+
"tie_word_embeddings": true,
|
161 |
+
"tokenizer_class": null,
|
162 |
+
"top_k": 50,
|
163 |
+
"top_p": 1.0,
|
164 |
+
"torch_dtype": null,
|
165 |
+
"torchscript": false,
|
166 |
+
"transformers_version": "4.26.0.dev0",
|
167 |
+
"typical_p": 1.0,
|
168 |
+
"use_bfloat16": false
|
169 |
+
}
|
170 |
+
}
|
handler.py
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
from typing import Dict, Any
|
3 |
+
from PIL import Image
|
4 |
+
import torch
|
5 |
+
import base64
|
6 |
+
from io import BytesIO
|
7 |
+
from transformers import BlipForConditionalGeneration, BlipProcessor
|
8 |
+
|
9 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
10 |
+
|
11 |
+
|
12 |
+
class EndpointHandler:
|
13 |
+
def __init__(self, path=""):
|
14 |
+
self.processor = BlipProcessor.from_pretrained(
|
15 |
+
"Salesforce/blip-image-captioning-large"
|
16 |
+
)
|
17 |
+
self.model = BlipForConditionalGeneration.from_pretrained(
|
18 |
+
"Salesforce/blip-image-captioning-large"
|
19 |
+
).to(device)
|
20 |
+
self.model.eval()
|
21 |
+
|
22 |
+
def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
|
23 |
+
input_data = data.get("inputs", {})
|
24 |
+
encoded_images = input_data.get("images")
|
25 |
+
|
26 |
+
if not encoded_images:
|
27 |
+
return {"captions": [], "error": "No images provided"}
|
28 |
+
|
29 |
+
texts = input_data.get("texts", ["a photography of"] * len(encoded_images))
|
30 |
+
|
31 |
+
try:
|
32 |
+
raw_images = [
|
33 |
+
Image.open(BytesIO(base64.b64decode(img))).convert("RGB")
|
34 |
+
for img in encoded_images
|
35 |
+
]
|
36 |
+
processed_inputs = [
|
37 |
+
self.processor(image, text, return_tensors="pt")
|
38 |
+
for image, text in zip(raw_images, texts)
|
39 |
+
]
|
40 |
+
processed_inputs = {
|
41 |
+
"pixel_values": torch.cat(
|
42 |
+
[inp["pixel_values"] for inp in processed_inputs], dim=0
|
43 |
+
).to(device),
|
44 |
+
"input_ids": torch.cat(
|
45 |
+
[inp["input_ids"] for inp in processed_inputs], dim=0
|
46 |
+
).to(device),
|
47 |
+
"attention_mask": torch.cat(
|
48 |
+
[inp["attention_mask"] for inp in processed_inputs], dim=0
|
49 |
+
).to(device),
|
50 |
+
}
|
51 |
+
|
52 |
+
with torch.no_grad():
|
53 |
+
out = self.model.generate(**processed_inputs)
|
54 |
+
|
55 |
+
captions = self.processor.batch_decode(out, skip_special_tokens=True)
|
56 |
+
return {"captions": captions}
|
57 |
+
except Exception as e:
|
58 |
+
print(f"Error during processing: {str(e)}")
|
59 |
+
return {"captions": [], "error": str(e)}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_pad": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.48145466,
|
8 |
+
0.4578275,
|
9 |
+
0.40821073
|
10 |
+
],
|
11 |
+
"image_processor_type": "BlipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.26862954,
|
14 |
+
0.26130258,
|
15 |
+
0.27577711
|
16 |
+
],
|
17 |
+
"processor_class": "BlipProcessor",
|
18 |
+
"resample": 3,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 384,
|
22 |
+
"width": 384
|
23 |
+
},
|
24 |
+
"size_divisor": 32
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66c8aec8d91b5e74b86bde343ed95fb53e9ccf9ffc77c5093890df662d234e04
|
3 |
+
size 1879143921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "Salesforce/blip-image-captioning-large",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"processor_class": "BlipProcessor",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]",
|
17 |
+
"model_input_names": [
|
18 |
+
"input_ids",
|
19 |
+
"attention_mask"
|
20 |
+
]
|
21 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|