bamec66557/MISCHIEVOUS-12B-Mix_0.1v
Full fine-tune vs bamec66557/MISCHIEVOUS-12B. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 43/81, MLP 116/120, Attention 160/160
2 derivatives checked
- mradermacher/MISCHIEVOUS-12B-Mix_0.1v-GGUF: Quantization
- bamec66557/MISCHIEVOUS-12B-Mix_0.3v: Partial fine-tune