xwen-team/Xwen-7B-Chat
Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1
5 derivatives checked
- mradermacher/Xwen-7B-Chat-i1-GGUF: Quantization
- xwen-team/Xwen-7B-Chat-i1-GGUF: Quantization
- mradermacher/Xwen-7B-Chat-GGUF: Same weights, converted
- xwen-team/Xwen-7B-Chat-GGUF: Same weights, converted
- DevQuasar-7/xwen-team.Xwen-7B-Chat-GGUF: Same weights, converted