mmaaz60 commited on
Commit
7491659
1 Parent(s): 8160f4c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -10,6 +10,10 @@
10
 
11
  This repository features LLaVA v1.5 trained with the Meta-Llama-3-8B-Instruct LLM. This integration aims to leverage the strengths of both models to offer advanced vision-language understanding.
12
 
 
 
 
 
13
 
14
  ## Key Components
15
 
 
10
 
11
  This repository features LLaVA v1.5 trained with the Meta-Llama-3-8B-Instruct LLM. This integration aims to leverage the strengths of both models to offer advanced vision-language understanding.
12
 
13
+ ## Training Strategy
14
+ - **Pretraining:** Only Vision-to-Language projector is trained. The rest of the model is frozen.
15
+ - **Fine-tuning:** LLM is LoRA fine-tuned. Only the vision-backbone (CLIP) is kept frozen.
16
+ - **Note:** The repository contains merged weights.
17
 
18
  ## Key Components
19