async-grpo-ckpt-smoke-r1d-1.5b

Description

async-grpo-ckpt-smoke-r1d-1.5b is an open-weight text-generation model with roughly 1.5B parameters published by aminediroHF on the Hugging Face Hub. It has 1,613 downloads. Runs with transformers.

Categories

• Productivity

Tags

• qwen2
• text-generation
• generated_from_trainer
• trackio:https://huggingface.co/spaces/aminediroHF/async-grpo-ckpt-smoke-static-053862
• trackio
• hf_jobs
• async-grpo
• trl

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1.5B parameters