Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: visual-question-answering
|
|
15 |
|
16 |
## Model
|
17 |
|
18 |
-
llava-v1.5-7b-xtuner-pretrain is a LLaVA projector pretrained from [Vicuna-v1.5
|
19 |
|
20 |
The fine-tuned LLaVA model can be found on [xtuner/llava-v1.5-7b-xtuner](https://huggingface.co/xtuner/llava-v1.5-7b-xtuner).
|
21 |
|
|
|
15 |
|
16 |
## Model
|
17 |
|
18 |
+
llava-v1.5-7b-xtuner-pretrain is a LLaVA projector pretrained from [Vicuna-7B-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) on [LLaVA-Pretrain](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain) dataset by [XTuner](https://github.com/InternLM/xtuner).
|
19 |
|
20 |
The fine-tuned LLaVA model can be found on [xtuner/llava-v1.5-7b-xtuner](https://huggingface.co/xtuner/llava-v1.5-7b-xtuner).
|
21 |
|