aimagelab/LLaVA_MORE-llama_3_1-8B-pretrain
Image-Text-to-Text
•
Updated
•
5
LLaVA-MORE
LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
-
-
aimagelab/LLaVA_MORE-llama_3_1-8B-finetuning
Image-Text-to-Text • 8B • Updated • 1.28k • 11 -
aimagelab/LLaVA_MORE-llama_3_1-8B-siglip-pretrain
Image-Text-to-Text • Updated • 14 -
aimagelab/LLaVA_MORE-llama_3_1-8B-siglip-finetuning
Image-Text-to-Text • 8B • Updated • 10 • 1 -
aimagelab/LLaVA_MORE-llama_3_1-8B-S2-pretrain
Image-Text-to-Text • Updated • 3 -
aimagelab/LLaVA_MORE-llama_3_1-8B-S2-finetuning
Image-Text-to-Text • 8B • Updated • 5 -
aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-pretrain
Image-Text-to-Text • Updated • 3 -
aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-finetuning
Image-Text-to-Text • 8B • Updated • 39 • 2 -
aimagelab/LLaVA_MORE-phi_4-finetuning
Text Generation • 4B • Updated • 4 -
aimagelab/LLaVA_MORE-gemma_2_9b-finetuning
Text Generation • 10B • Updated • 4 -
aimagelab/LLaVA_MORE-gemma_2_9b-siglip2-finetuning
Text Generation • 10B • Updated • 5 -
aimagelab/LLaVA_MORE-llama_3_1-reasoning-finetuning
Text Generation • 8B • Updated • 4