vanilj / reflection-70b-iq2_xxs

Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

70B

194 Pulls Updated 13 days ago

params

290615e13f21 · 127B

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>" ], "temperature": 0.7, "top_p": 0.95 }