cubukcum/gpt-oss-120b-reasoning

Uploaded finetuned model

• Developed by: cubukcum
• License: apache-2.0
• Finetuned from model: unsloth/gpt-oss-120b-unsloth-bnb-4bit

Training Details

This model was fine-tuned using the AM-DeepSeek-R1-Distilled-1.4M dataset.

• Dataset Subset: am_0.5M
• Training Duration: 0.5 epochs
• Hardware Used: NVIDIA H200 GPU

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