PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
Full fine-tune vs mistralai/Mistral-Nemo-Base-2407. 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
18 derivatives checked
- bartowski/Dans-PersonalityEngine-V1.1.0-12b-GGUF: Same weights, converted
- BasedAGI/Dans-PersonalityEngine-V1.1.0-12B-i1-GGUF: Quantization
- mradermacher/Dans-PersonalityEngine-V1.1.0-12b-i1-GGUF: Quantization
- mradermacher/Dans-PersonalityEngine-V1.1.0-12b-GGUF: Quantization
- MaziyarPanahi/Dans-PersonalityEngine-V1.1.0-12b-GGUF: Same weights, converted
- featherless-ai-quants/PocketDoc-Dans-PersonalityEngine-V1.1.0-12b-GGUF: Quantization
- PocketDoc/Dans-SakuraKaze-V1.0.0-12b: Full fine-tune
- WokeAI/Tankie-DPE-12B-SFT-v2: Full fine-tune
- DoppelReflEx/MN-12B-Mimicore-GreenSnake: Full fine-tune
- yamatazen/SnowElf-12B: Full fine-tune
- yamatazen/KnowledgeCore-12B: Partial fine-tune
- ewald1976/Corridor-C-12B: Full fine-tune
- yamatazen/BlueLight-12B: Full fine-tune
- WokeAI/Tankie-DPE-12b-SFT: Full fine-tune
- Delta-Vector/Francois-PE-V2: LoRA-style
- yamatazen/ElvenMaid-12B: Full fine-tune
- BarBarickoza/Dans-Picaro-MagNante-v4-v1-12b-V3: Full fine-tune
- Tokerss/PockedAndFandomDxd: LoRA-style