14B open-weight LLM by akshay-sked
GRPO-Lora-Trained-Qwen3-14b is an open-weight text-generation model with roughly 14B parameters published by akshay-sked on the Hugging Face Hub. It has 349 downloads. Runs with peft.
akshay-sked
api
free
Others in the same category, ranked by how often they are opened.
