huihui-ai/Huihui-gpt-oss-20b-mxfp4-abliterated-v2
Same weights, repacked vs huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated-v2. Same weights in different files (re-saved, re-sharded or new metadata), plus 96 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/96, Attention 0/216, lm_head 0/1
4 derivatives checked
- pinecoresystems/Huihui-gpt-oss-20b-mxfp4-abliterated-v2: Same weights, converted
- nightmedia/Huihui-gpt-oss-20b-mxfp4-abliterated-v2-qx86-hi-mlx: Quantization
- DavidAU/OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4: LoRA-style
- FlatFootInternational/Huihui-gpt-oss-20b-mxfp4-abliterated-v2-mlx-fp16: Quantization