Experimental model doing a DPO training on top of Kunoichi-DPO-v2-7b, i.e. double-DPO.

7B

152 Pulls Updated 3 months ago

4ddf52c3a1ac · 146B
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>", "<|reserved_special_token" ], "temperature": 0.6 }