dndll/GRM-2.6-Opus-Heretic-Abliterated-MTP
LoRA-style vs OrionLLM/GRM-2.6-Opus. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of conv1d, down_proj, o_proj, out_proj changed, in 54 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, Norms 0/325, Attention 62/560, MLP 36/307, other 0/1
2 derivatives checked
- mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-i1-GGUF: Quantization
- mradermacher/GRM-2.6-Opus-Heretic-Abliterated-MTP-GGUF: Quantization