gpt-oss-120b
OpenAIAfter pre-training, we post-train the models using similar CoT RL techniques as OpenAI o3.
1 more from this model
After pre-training, we post-train the models using similar CoT RL techniques as OpenAI o3.
general family · filed under post-training
Reinforcement-learning post-training using techniques described as similar to OpenAI o3's CoT RL.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reinforcement learning algorithm for the methods filed beside it.
Also called similar CoT RL techniques as OpenAI o3.
2 quotes from 2 sources, one card per model, each opening with its strongest.
After pre-training, we post-train the models using similar CoT RL techniques as OpenAI o3.
After pre-training, we post-train the models using similar CoT RL techniques as OpenAI o3.