tahamajs
/

llama-3.2-3b-dpo-lora64-4bit-instruct

Model card Files Files and versions Metrics Training metrics Community

llama-3.2-3b-dpo-lora64-4bit-instruct

Commit History

Upload DPO fine-tuned checkpoint

55e954e
verified

tahamajs commited on Apr 3

Tokenizer for DPO model (Trained with Unsloth)

57bf03b
verified

tahamajs commited on Apr 3

Initial commit of DPO model after training

484ad1b
verified

tahamajs commited on Apr 3

initial commit

dcf8f72
verified

tahamajs commited on Apr 3