
This is the LoRA on llava-hf/llama3-llava-next-8b-hf, simple vision version of reproduce Mol-Instruct model, under the same dataset with full size text dataset, this is a text alignment reproduce version.
3acfc6c
verified
{ | |
"image_token": "<image>", | |
"num_additional_image_tokens": 1, | |
"patch_size": 14, | |
"processor_class": "LlavaNextProcessor", | |
"vision_feature_select_strategy": "default" | |
} | |