NOIRAgentic/qwopus-omnicoder-abliterated
LoRA-style vs Jackrong/Qwopus3.5-9B-v3. 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, out_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 56/336, other 0/1, Norms 0/221
2 derivatives checked
- mradermacher/qwopus-omnicoder-abliterated-i1-GGUF: Quantization
- mradermacher/qwopus-omnicoder-abliterated-GGUF: Same weights, converted