Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
SakanaAI
/
Llama-3-EvoVLM-JP-v2
like
14
Image-to-Text
Transformers
Safetensors
Japanese
llava
pretraining
multimodal
vision-language
mantis
llama3
siglip
Inference Endpoints
arxiv:
2403.13187
License:
llama3
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
main
Llama-3-EvoVLM-JP-v2
/
model-00002-of-00004.safetensors
Commit History
Upload LlavaForConditionalGeneration
9cf9a20
verified
Inoichan
commited on
16 days ago
Inoichan
commited on
