4B open-weight LLM by yuhan-nlp
verl-grpo-medium-qwen3-4b-step50-repro is an open-weight text-generation model with roughly 4B parameters published by yuhan-nlp on the Hugging Face Hub. It has 317 downloads. Runs with transformers.
yuhan-nlp
api
free
Others in the same category, ranked by how often they are opened.
