prithivMLmods/Sombrero-QwQ-32B-Elite11
Full fine-tune vs Qwen/QwQ-32B. Fine-tune: 99% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 128/129, MLP 189/192, Attention 441/448, lm_head 1/1
3 derivatives checked
- BasedAGI/Sombrero-QwQ-32B-Elite11-i1-GGUF: Quantization
- mradermacher/Sombrero-QwQ-32B-Elite11-i1-GGUF: Quantization
- mradermacher/Sombrero-QwQ-32B-Elite11-GGUF: Quantization