weizhiwang
/

llava-v1.5-llama-3-8b-pretrain-clip-large

Text Generation

Model card Files Files and versions Community

weizhiwang commited on Apr 24

Commit

3d6c9fb

•

1 Parent(s): aadbfba

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,4 +16,4 @@ Please follow my reproduced implementation [LLaVA-Llama-3](https://github.com/Vi
 ## Architecture
 - LLM: llama-3-8b (Frozen)
 - Vision-Language Adapter: MLP
-- Vision Encoder: CLIP-ViT-L-336px (Frozen)

 ## Architecture
 - LLM: llama-3-8b (Frozen)
 - Vision-Language Adapter: MLP
+- Vision Encoder: CLIP-ViT-L (Frozen)