Neroism8422's picture
This is the LoRA on meta-llama/Meta-Llama-3-8B-Instruct, simple vision version of reproduce Mol-Instruct model, under the same dataset with full size text dataset, this is a text alignment reproduce version.
fce9d26 verified
raw
history blame contribute delete
177 Bytes
{
"image_token": "<image>",
"num_additional_image_tokens": 1,
"patch_size": 14,
"processor_class": "LlavaNextProcessor",
"vision_feature_select_strategy": "default"
}