Hugging Face's logo

YipengZhang
/
LLaVA-UHD-v2-Vicuna-7B

Image-Text-to-Text
Transformers
Safetensors
llava_llama
text-generation
Model card Files Community
YipengZhang commited on
Commit
28eb9c5
·
verified ·
1 Parent(s): d859e94

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -43,7 +43,7 @@ The primary use of LLaVA-UHD v2 is research on large multimodal models and chatb
43
  The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
44
 
45
  ## Training dataset
46
- - JBU Pretrain: MS-COCO stuff 2017
47
  - Pretrain: LLaVA-Pretrain 558K (filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.)
48
  - SFT: 858k-mixed dataset in https://huggingface.co/datasets/YipengZhang/LLaVA-UHD-v2-SFT-Data
49
 
 
43
  The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
44
 
45
  ## Training dataset
46
+ - VDIM Pretrain: MS-COCO stuff 2017
47
  - Pretrain: LLaVA-Pretrain 558K (filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.)
48
  - SFT: 858k-mixed dataset in https://huggingface.co/datasets/YipengZhang/LLaVA-UHD-v2-SFT-Data
49