win10/Verdandi-Qwen2.5-7B
Partial fine-tune vs C10X/LongWriter-Qwen2.5-7B-Instruct. Partial change: 82% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 11/57, MLP 72/84, Attention 144/196, lm_head 1/1
2 derivatives checked
- mradermacher/Verdandi-Qwen2.5-7B-i1-GGUF: Quantization
- mradermacher/Verdandi-Qwen2.5-7B-GGUF: Same weights, converted