openai/gpt-oss-safeguard-120b
Partial fine-tune vs openai/gpt-oss-120b. Partial change: 58% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: MLP 182/288, Norms 73/73, Attention 269/324, lm_head 1/1, Embeddings 1/1
5 derivatives checked
- lmstudio-community/gpt-oss-safeguard-120b-MLX-MXFP4: Quantization
- unsloth/gpt-oss-safeguard-120b-GGUF: Quantization
- lmstudio-community/gpt-oss-safeguard-120b-GGUF: Quantization
- Seriki/Lmlm: Quantization
- PoSTMEDIA/Vayne-V3-Pro: Full fine-tune
3 other repos hold byte-for-byte identical weight files.