DavidAU/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored
LoRA-style vs coder3101/gpt-oss-20b-heretic. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/144, Attention 96/216, lm_head 0/1
7 derivatives checked
- mradermacher/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-i1-GGUF: Quantization
- xiastralstar/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-i1-GGUF: Quantization
- mradermacher/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-GGUF: Quantization
- fairy322/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-i1-GGUF: Quantization
- matrixdose/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-i1-GGUF: Quantization
- Lachhhhhhh/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-Q4_K_S-GGUF: Quantization
- BoneMangler/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-Q6_K-GGUF: Quantization