SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
LoRA-style vs allura-org/MN-12b-RP-Ink. 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: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 0/1
7 derivatives checked
- mradermacher/MN-12b-RP-Ink-RP-Longform-i1-GGUF: Quantization
- mradermacher/MN-12b-RP-Ink-RP-Longform-GGUF: Quantization
- EldritchLabs/MN-12B-RP-Ink-Longform-MPOA: Abliterated
- Vortex5/Wicked-Nebula-12B: Full fine-tune
- Vortex5/Chaos-Unknown-12b: Full fine-tune
- Vortex5/Cosmic-Night-12B: Full fine-tune
- Vortex5/Shining-Seraph-12B: Full fine-tune