lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct download history
lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct is an 8.5B-parameter image text to text model by lmms-lab-encoder. In the last 30 days it was downloaded 5,409 times (1,858 in the last 7 days), and 201,781 times in total.
It ranks #11,859 on the Hub by monthly downloads and #1,409 among image text to text models.
It has 17 likes.
2 models build on LLaVA-OneVision-2-8B-Instruct: 0 quantized, 1 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 5,418 times in the last 30 days. See the LLaVA-OneVision-2-8B-Instruct galaxy.
Most downloaded derivatives
- PVIS2027-JT-6597/LLaVA-OneVision-2-8B-SciVisCap (adapter), 9 downloads in 30 days
- lakelee/2026e-anticipation-v5-lf-c0attn-llava (finetune), 0 downloads in 30 days
Open lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.