Video LLM based on Llama-3 and Llama-3.1
Weizhi Wang
weizhiwang
AI & ML interests
None yet
Organizations
Collections
3
Reproduction of various LLaVA models based on LLaMA-3 backbone.
-
weizhiwang/LLaVA-Llama-3-8B
Text Generation • Updated • 65 • 15 -
weizhiwang/LLaVA-Video-Llama-3
Video-Text-to-Text • Updated • 364 • 4 -
weizhiwang/llava-v1.5-llama-3-8b-pretrain-clip-large
Text Generation • Updated • 14 • 2 -
weizhiwang/llava-v1.5-llama-3-8b-pretrain-clip-large-336px
Text Generation • Updated • 15 • 1
models
13
weizhiwang/LLaVA-Llama-3-8B
Text Generation
•
Updated
•
65
•
15
weizhiwang/LLaVA-Video-Llama-3.1-8B
Updated
•
50
•
1
weizhiwang/LLaVA-Video-Llama-3
Video-Text-to-Text
•
Updated
•
364
•
4
weizhiwang/Video-Language-Model-Average-Pooling-Projector
Updated
•
3
weizhiwang/llava-v1.5-phi-3-mini-pretrain-clip-large-336px
Text Generation
•
Updated
•
7
weizhiwang/LaViA-Llama-3-8b
Text Generation
•
Updated
•
5
•
1
weizhiwang/mlm-filter-llava-llama-3-8b-gpt4v
Text Generation
•
Updated
•
11
•
1
weizhiwang/llava-v1.5-llama-3-8b-pretrain-clip-large-336px
Text Generation
•
Updated
•
15
•
1
weizhiwang/llava-v1.5-llama-3-8b-pretrain-clip-large
Text Generation
•
Updated
•
14
•
2
weizhiwang/mlm-filter-llava-13b-gpt4v
Text Generation
•
Updated
•
14
•
6