TheDrummer/Skyfall-31B-v4.2
Full fine-tune vs mistralai/Magistral-Small-2509. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 32/81, MLP 120/120, Attention 160/160, lm_head 1/1
6 derivatives checked
- bartowski/TheDrummer_Skyfall-31B-v4.2-GGUF: Same weights, converted
- mradermacher/Skyfall-31B-v4.2-i1-GGUF: Quantization
- mradermacher/Skyfall-31B-v4.2-GGUF: Quantization
- Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF: Same weights, converted
- Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF: Same weights, converted
- coder3101/Skyfall-31B-v4.2-heretic: Abliterated
1 other repos hold byte-for-byte identical weight files.