Qwen3.5 9B Coder

This is a experimental finetune on a mix of many traces from many different models. Reasoning was left untouched.

Total train time: ~4 hours

Training Script

The data for this model was easily formatted and masked with Teich

• Developed by: armand0e
• License: apache-2.0
• Finetuned from model : Qwen/Qwen3.5-9B

This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.

👁 Image

Base model