tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft
Full fine-tune vs Qwen/Qwen2.5-Coder-0.5B-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 72/72, Attention 168/168
3 derivatives checked
- MaziyarPanahi/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF: Same weights, converted
- mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF: Quantization
- mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-GGUF: Same weights, converted