win10/Urdandi-Qwen2.5-7B
Full fine-tune vs win10/Urd-Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 22/57, MLP 84/84, Attention 196/196
2 derivatives checked
- mradermacher/Urdandi-Qwen2.5-7B-i1-GGUF: Quantization
- mradermacher/Urdandi-Qwen2.5-7B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.