bamec66557/MISCHIEVOUS-12B-Mix_0.4v
Partial fine-tune vs bamec66557/MISCHIEVOUS-12B-Mix_0.3v. Partial change: 50% of the weights changed (attention, embeddings, mlp, norms), in 20 of 40 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 18/81, MLP 60/120, Attention 80/160
7 derivatives checked
- mradermacher/MISCHIEVOUS-12B-Mix_0.4v-i1-GGUF: Quantization
- mradermacher/MISCHIEVOUS-12B-Mix_0.4v-GGUF: Quantization
- MaziyarPanahi/MISCHIEVOUS-12B-Mix_0.4v-GGUF: Same weights, converted
- bamec66557/MISCHIEVOUS-12B-Mix_0.6v: Full fine-tune
- bamec66557/MISCHIEVOUS-12B-Mix_Neo: Partial fine-tune
- bamec66557/VICIOUS_MESH-12B-ALPHA: Partial fine-tune
- bamec66557/MISCHIEVOUS-12B-Mix_III_IV_V: Full fine-tune