PocketDoc/Dans-PersonalityEngine-V1.3.0-12b
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 80/81, MLP 120/120, Attention 160/160, lm_head 1/1
15 derivatives checked
- bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-12b-GGUF: Same weights, converted
- mradermacher/Dans-PersonalityEngine-V1.3.0-12b-i1-GGUF: Quantization
- IggyLux/MN-VelvetCafe-RP-12B-V2-Q4_K_M-GGUF: Full fine-tune
- mradermacher/Dans-PersonalityEngine-V1.3.0-12b-GGUF: Quantization
- tensorblock/PocketDoc_Dans-PersonalityEngine-V1.3.0-12b-GGUF: Quantization
- IggyLux/MN-VelvetCafe-RP-12B-V2-Q8_0-GGUF: Full fine-tune
- IggyLux/MN-VelvetCafe-RP-12B-Q4_K_M-GGUF: Full fine-tune
- Casual-Autopsy/Dans-PersonalityEngine-V1.3.0-12b-imat-GGUFs: Quantization
- IggyLux/MN-VelvetCafe-RP-12B-V2: Full fine-tune
- IggyLux/MN-VelvetCafe-RP-12B: Full fine-tune
- Snqwii/mag-pe-dt: Full fine-tune
- Snqwii/Bigger-Personality-12B: Full fine-tune
- pot99rta/PatriMaidV2-12B: Full fine-tune
- mergekit-community/mergekit-slerp-srinwor: Full fine-tune
- Sorihon/Dans-PersonalityEngine-V1.3.0-12B-Heretic: Abliterated
1 other repos hold byte-for-byte identical weight files.