Reflection Llama-3.1 70B is trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
The model was trained on synthetic data.
Modalities
Context
131K
Released
Sep 6, 2024
Knowledge Cutoff
Dec 2023
Token volume and request traffic to this model over time.
Reflection Llama-3.1 70B is trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course. The model was trained on synthetic data.
Reflection 70B has a 131,072 token context window.
Reflection 70B was released on September 6, 2024. Its knowledge cutoff is December 31, 2023.