tencent/UI-Mate-9B
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 89% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 3/4, MLP 188/208, Attention 296/332, Norms 138/215
5 derivatives checked
- bartowski/tencent_UI-Mate-9B-GGUF: Same weights, converted
- mradermacher/UI-Mate-9B-i1-GGUF: Quantization
- prithivMLmods/UI-Mate-9B-GGUF: Same weights, converted
- mradermacher/UI-Mate-9B-GGUF: Same weights, converted
- DevQuasar/tencent.UI-Mate-9B-GGUF: Quantization