fireworks1231/qwen3-4b-3-sfted-grpo-h200-1200step

Source: 🤗text-generationapache-2.04B params8.0 GBsafetensors✓ 3 checksumsupdated 466d ago
or submit a torrent

Uploaded finetuned model

  • Developed by: quelmap
  • License: apache-2.0
  • Finetuned from model : quelmap/qwen3-4b-sft-pretrained

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.