TIGER-Lab/Mantis-8B-clip-llama3-pretraind

Model

stars

commits

linked in READMEs

May 3, 2024

updated

conversational

endpoints_compatible

generated_from_trainer

image-text-to-text

llava

safetensors

transformers

Browse cluster: Multimodal LLM Fine-tuning & Vision-Language Models →

README

See the Mantis-Instruct fine-tuned version here TIGER-Lab/Mantis-8B-clip-llama3. This checkpoint is just for experiments reproduction and does not serve as a functional model

Contributors

DongfuJiang

3 commits

Similar repos

TIGER-Lab/Mantis-8B-siglip-llama3-pretraind

Model

aimagelab/LLaVA_MORE-llama_3_1-8B-S2-pretrain

Model

aimagelab/LLaVA_MORE-llama_3_1-8B-siglip-pretrain

Model

aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-pretrain

Model

aimagelab/LLaVA_MORE-llama_3_1-8B-pretrain

Model

binxia/llmga-llama3-8b-it-full-finetune

Model

binxia/llmga-cn-llama3-8b-it-full-finetune

Model

meta-llama/Llama-3.2-11B-Vision-Instruct

Model

1,643

Linked in READMEs

TIGER-AI-Lab/Mantis

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

240

README badge