WokeAI/Tankie-DPE-12B-SFT-v2
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 30/81, MLP 120/120, Attention 160/160, lm_head 1/1
3 derivatives checked
- mradermacher/Tankie-DPE-12B-SFT-v2-i1-GGUF: Quantization
- mradermacher/Tankie-DPE-12B-SFT-v2-GGUF: Quantization
- ewald1976/Ostblock-12B: Full fine-tune