htlou/mm-interp-RLAIF-V-Dataset-llava-mistral download history

htlou/mm-interp-RLAIF-V-Dataset-llava-mistral is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 104 times (43 in the last 7 days), and 1,398 times in total. It ranks #111,637 among datasets by monthly downloads.

RLAIF-V-Dataset This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the RLAIF-V-Dataset dataset. It achieves the following results on the evaluation set: Loss: 0.4467 Rewards/chosen: -3.1988 Rewards/rejected: -5.9606 Rewards/accuracies: 0.8163 Rewards/margins: 2.76

Open htlou/mm-interp-RLAIF-V-Dataset-llava-mistral on Hugging Face

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