BenevolenceMessiah/Qwen2.5-Coder-7B-Chat-Instruct-TIES
Full fine-tune vs Qwen/Qwen2.5-Coder-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 36/57, MLP 84/84, Attention 176/196
2 derivatives checked
- mradermacher/Qwen2.5-Coder-7B-Chat-Instruct-TIES-GGUF: Same weights, converted
- mradermacher/Qwen2.5-Coder-7B-Chat-Instruct-TIES-i1-GGUF: Quantization