PocketDoc/Dans-SakuraKaze-V1.0.0-12b
Full fine-tune vs PocketDoc/Dans-PersonalityEngine-V1.1.0-12b. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 1/1
7 derivatives checked
- bartowski/PocketDoc_Dans-SakuraKaze-V1.0.0-12b-GGUF: Same weights, converted
- mradermacher/Dans-SakuraKaze-V1.0.0-12b-i1-GGUF: Quantization
- mradermacher/Dans-SakuraKaze-V1.0.0-12b-GGUF: Quantization
- featherless-ai-quants/PocketDoc-Dans-SakuraKaze-V1.0.0-12b-GGUF: Quantization
- Vortex5/Stellar-Witch-12B: Full fine-tune
- BeaverAI/MN-2407-DSK-QwQify-v0.1-12B: LoRA-style
- BarBarickoza/Dans-SakuraKaze-Picaro-12b: Full fine-tune