LatitudeGames/Wayfarer-2-12B
LoRA-style vs mistralai/Mistral-Nemo-Base-2407. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/81, MLP 120/120, Attention 160/160
10 derivatives checked
- LatitudeGames/Wayfarer-2-12B-GGUF: Same weights, converted
- bartowski/LatitudeGames_Wayfarer-2-12B-GGUF: Same weights, converted
- mradermacher/Wayfarer-2-12B-i1-GGUF: Quantization
- mradermacher/Wayfarer-2-12B-GGUF: Quantization
- DevQuasar/LatitudeGames.Wayfarer-2-12B-GGUF: Same weights, converted
- MuXodious/Wayfarer-2-12B-absolute-heresy: Abliterated
- DarkArtsForge/Protocol-Phantom-12B: Full fine-tune
- mergekit-community/Arisu-12B: Full fine-tune
- Retreatcost/Lorablated-w2bb-psy-della: Full fine-tune
- mergekit-community/Alicer-12B: Full fine-tune