Full talk · edited transcript

How We Do RL for Our LLM at Avito

Albert Akopyan23 May 2026

Author: Albert Akopyan, Core LLM team, Avito.tech.

A talk about how Avito post-trains its own base model built on open weights: a custom tokenizer, SFT and RL with verifiable rewards (RLVR) in three domains, a change of training framework when moving to MoE, and engineering techniques for GRPO.

Continue reading — it's free

Google or a one-time email code. No password.