4B open-weight LLM by shubhamrgandhi
Qwen3-4B-DPO-prm-pairs is an open-weight text-generation model with roughly 4B parameters published by shubhamrgandhi on the Hugging Face Hub. It has 382 downloads. Runs with transformers.
shubhamrgandhi
api
free
Others in the same category, ranked by how often they are opened.
