Mawdistical-S1/Infracelestial-27B
Full fine-tune vs ArliAI/Qwen3.5-27B-Derestricted. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: lm_head 1/1, Embeddings 3/5, MLP 251/307, Attention 410/560, other 1/1, Norms 0/325
3 derivatives checked
- bartowski/Mawdistical-S1_Infracelestial-27B-GGUF: Same weights, converted
- mradermacher/Infracelestial-27B-i1-GGUF: Quantization
- mradermacher/Infracelestial-27B-GGUF: Quantization