Upload 4 files
Browse files- README.md +44 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
inference: false
|
3 |
+
pipeline_tag: image-text-to-text
|
4 |
+
---
|
5 |
+
|
6 |
+
<br>
|
7 |
+
<br>
|
8 |
+
|
9 |
+
# LLaVA Model Card
|
10 |
+
|
11 |
+
## Model details
|
12 |
+
|
13 |
+
**Model type:**
|
14 |
+
LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.
|
15 |
+
It is an auto-regressive language model, based on the transformer architecture.
|
16 |
+
|
17 |
+
**Model date:**
|
18 |
+
LLaVA-v1.5-13B was trained in September 2023.
|
19 |
+
|
20 |
+
**Paper or resources for more information:**
|
21 |
+
https://llava-vl.github.io/
|
22 |
+
|
23 |
+
## License
|
24 |
+
Llama 2 is licensed under the LLAMA 2 Community License,
|
25 |
+
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
26 |
+
|
27 |
+
**Where to send questions or comments about the model:**
|
28 |
+
https://github.com/haotian-liu/LLaVA/issues
|
29 |
+
|
30 |
+
## Intended use
|
31 |
+
**Primary intended uses:**
|
32 |
+
The primary use of LLaVA is research on large multimodal models and chatbots.
|
33 |
+
|
34 |
+
**Primary intended users:**
|
35 |
+
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
36 |
+
|
37 |
+
## Training dataset
|
38 |
+
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
|
39 |
+
- 158K GPT-generated multimodal instruction-following data.
|
40 |
+
- 450K academic-task-oriented VQA data mixture.
|
41 |
+
- 40K ShareGPT data.
|
42 |
+
|
43 |
+
## Evaluation dataset
|
44 |
+
A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|