shi-labs/pretrain_dsg_OLA-VLM-CLIP-ViT-Llama3-8b download history

shi-labs/pretrain_dsg_OLA-VLM-CLIP-ViT-Llama3-8b is an 8.5B-parameter image text to text model by shi-labs. In the last 30 days it was downloaded 15 times (6 in the last 7 days), and 517 times in total.

It ranks #539,606 on the Hub by monthly downloads and #21,485 among image text to text models.

It has 0 likes.

It is a fine-tune of meta-llama/Meta-Llama-3-8B-Instruct.

1 models build on pretrain_dsg_OLA-VLM-CLIP-ViT-Llama3-8b: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 31 times in the last 30 days. See the pretrain_dsg_OLA-VLM-CLIP-ViT-Llama3-8b galaxy.

Most downloaded derivatives

Open shi-labs/pretrain_dsg_OLA-VLM-CLIP-ViT-Llama3-8b on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.