Harmony chat template

Hold

Techniques

The chat formatting and conversation semantics used by GPT-OSS during training and inference.

Why it's here

Placed in Hold: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.

Evidence (1)

6Hugging Face Blog·1/27/2026research
Hugging Face details agentic RL training for GPT-OSS
Hugging Face describes a practical retrospective on enabling agentic reinforcement learning training for GPT-OSS, focusing on multi-step tool use, rollout generation, and reward-driven policy updates. The team highlights compatibility challenges with the Harmony chat template and evaluates the setup using verl, ReTool, gsm8k, and other verifiable tasks.