nbeerbower/Huihui-Qwen3.5-9B-abliterated-TIES-Hemlock-SFT
LoRA-style vs nbeerbower/Huihui-Qwen3.5-9B-abliterated-TIES. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/215, Attention 32/332, MLP 96/208
3 derivatives checked
- mradermacher/Huihui-Qwen3.5-9B-abliterated-TIES-Hemlock-SFT-i1-GGUF: Quantization
- mradermacher/Huihui-Qwen3.5-9B-abliterated-TIES-Hemlock-SFT-GGUF: Same weights, converted
- fairy322/Huihui-Qwen3.5-9B-abliterated-TIES-Hemlock-SFT-GGUF: Same weights, converted