Qwen2.5-Coder-7B-20260218
Collection
Experimental Qwen2.5-Coder-7B models distilled from gpt-oss-20b with 100 responses. A lite series exploring data-efficient knowledge transfer. • 3 items • Updated
Uploaded finetuned model
- Developed by: igarin
- License: cc-by-nc-4.0
- Finetuned from model : unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
Qwen2.5-Coder-7B-20260218-MLX
This repository contains MLX quantized weights for 2, 4, 5, 6, and 8 bits.
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Hardware compatibility
Log In to add your hardware
Quantized