Vision-CAIR/LongVU_Qwen2_7B download history
Vision-CAIR/LongVU_Qwen2_7B is a 7.7B-parameter video text to text model by Vision-CAIR. In the last 30 days it was downloaded 239 times (59 in the last 7 days), and 13,287 times in total.
It ranks #106,867 on the Hub by monthly downloads and #78 among video text to text models.
It has 76 likes.
It is a fine-tune of Vision-CAIR/LongVU_Qwen2_7B_img.
1 models build on LongVU_Qwen2_7B: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 248 times in the last 30 days. See the LongVU_Qwen2_7B galaxy.
Most downloaded derivatives
- pritamqu/LongVU_Qwen2_7B-RRPO-16f (finetune), 9 downloads in 30 days
Open Vision-CAIR/LongVU_Qwen2_7B on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.