mannix / gemma2-9b-simpo

Fine-tuned google/gemma-2-9b-it on princeton-nlp/gemma2-ultrafeedback-armorm with the SimPO objective.

343 Pulls Updated 7 weeks ago

params

1f0c17ce1cdb · 118B

{ "num_ctx": 4096, "num_predict": 4096, "repeat_penalty": 1, "stop": [ "<start_of_turn>", "<end_of_turn>" ] }