TheDrummer/Skyfall-31B-v4.1
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 31/81, MLP 120/120, Attention 160/160, lm_head 1/1
10 derivatives checked
- bartowski/TheDrummer_Skyfall-31B-v4.1-GGUF: Same weights, converted
- mradermacher/Skyfall-31B-v4.1-i1-GGUF: Quantization
- Silicone-Moss/TheDrummer-Skyfall-31B-v4.1-Heretic-Absolute-GGUF: Quantization
- mradermacher/Skyfall-31B-v4.1-GGUF: Quantization
- Silicone-Moss/TheDrummer-Skyfall-31B-v4.1-Heretic-Clear-GGUF: Quantization
- McG-221/Skyfall-31B-v4.1-mlx-8Bit: Quantization
- grayarea/Skyfall-31B-v4.1-Heretic-v1.2: Abliterated
- Silicone-Moss/TheDrummer-Skyfall-31B-v4.1-Heretic-Clear: Abliterated
- Silicone-Moss/TheDrummer-Skyfall-31B-v4.1-Heretic-Absolute: Abliterated
- zeroxjason200/TheDrummer_Skyfall-31B-SLERP-v4.1_v4.2-60_40: Full fine-tune
1 other repos hold byte-for-byte identical weight files.