mergekit-community/Slush-FallMix-Fire_Edition_1.0-12B
Partial fine-tune vs mergekit-community/Slush-ChatWaifu-Chronos. Partial change: 85% of the weights changed (attention, mlp, norms), in 38 of 40 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 38/81, MLP 114/120, Attention 152/160
2 derivatives checked
- mradermacher/Slush-FallMix-Fire_Edition_1.0-12B-i1-GGUF: Quantization
- mradermacher/Slush-FallMix-Fire_Edition_1.0-12B-GGUF: Quantization