huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated-v2
Full fine-tune vs huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated. Fine-tune: 99% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 0/49, MLP 113/144, Attention 189/216, lm_head 1/1
6 derivatives checked
- huihui-ai/Huihui-gpt-oss-20b-mxfp4-abliterated-v2: Same weights, repacked
- mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-GGUF: Quantization
- mradermacher/Huihui-gpt-oss-20b-BF16-abliterated-v2-i1-GGUF: Quantization
- noctrex/Huihui-gpt-oss-20b-abliterated-v2-MXFP4_MOE-GGUF: Quantization
- blascotobasco/GPT-OSS-20E-Abliterated: Same weights, repacked
- blascotobasco/GPT-OSS-26E-Abliterated: Same weights, repacked