Azazelle/MN-Halide-12b-v1.0
Full fine-tune vs Epiculous/Azure_Dusk-v0.2. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 34/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/MN-Halide-12b-v1.0-i1-GGUF: Quantization
- mradermacher/MN-Halide-12b-v1.0-GGUF: Quantization
- Khetterman/AbominationScience-12B-v4: Full fine-tune
- mergekit-community/MN-Sappho-k-12B: Full fine-tune