tsavage68/DPO_DSLlama_1000steps_01beta_1e6lr download history
tsavage68/DPO_DSLlama_1000steps_01beta_1e6lr is an 8.0B-parameter text generation model by tsavage68. In the last 30 days it was downloaded 10 times (6 in the last 7 days), and 48 times in total.
It ranks #773,389 on the Hub by monthly downloads and #289,469 among text generation models.
It has 0 likes.
It is a fine-tune of tsavage68/Hand_off_DS_Llama8B_100steps_1e6rate_SFT.
Open tsavage68/DPO_DSLlama_1000steps_01beta_1e6lr on Hugging Face