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.
f8d6513
verified
| { | |
| "bos_token": { | |
| "content": "<|begin_of_text|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|eot_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "image_token": "<image>", | |
| "pad_token": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |