This is the basic llava version of the original mol-instruct model, none tuned with only vision encoder of CLIP add on. aea55e2 verified Neroism8422 commited on Jun 29, 2025
This is the basic llava version of the original mol-instruct model, none tuned with only vision encoder of CLIP add on. 9c2bc74 verified Neroism8422 commited on Jun 29, 2025
This is the basic llava version of the original mol-instruct model, none tuned with only vision encoder of CLIP add on. e9d81d6 verified Neroism8422 commited on Jun 29, 2025