3B open-weight LLM by Jinhe
ReflectRL-Qwen2.5-3B-Instruct-GRPO is an open-weight text-generation model with roughly 3B parameters published by Jinhe on the Hugging Face Hub. It has 252 downloads. Runs with transformers.
Jinhe
api
free
Others in the same category, ranked by how often they are opened.
