huizimao/gpt-oss-20b-uncensored-bf16
LoRA-style vs openai/gpt-oss-20b. 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: Norms 0/49, MLP 0/96, Attention 96/216, lm_head 0/1, Embeddings 0/1
5 derivatives checked
- DavidAU/OpenAi-GPT-oss-20b-MODERATE-uncensored-NEO-Imatrix-gguf: Quantization
- mradermacher/gpt-oss-20b-uncensored-bf16-i1-GGUF: Quantization
- mradermacher/gpt-oss-20b-uncensored-bf16-GGUF: Quantization
- DavidAU/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored: Partial fine-tune (fewer layers)
- NikolayKozloff/gpt-oss-20b-uncensored-bf16-Q4_K_M-GGUF: Quantization