darkc0de/RICO-v2
LoRA-style vs DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU. 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 63 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, Norms 0/325, Attention 64/560, MLP 192/307, other 0/1
3 derivatives checked
- mradermacher/RICO-v2-i1-GGUF: Quantization
- mradermacher/RICO-v2-GGUF: Quantization
- otherwhere1/RICO-v2-mlx-8Bit: Quantization