Myric/gpt-oss-78B-GGUF
Same weights, converted vs openai/gpt-oss-120b. Same weights stored in another dtype (U8/BF16 → MXFP4/BF16), plus 252 new tensors.
Tensors changed: Norms 0/73, Attention 0/288, lm_head 0/1, Embeddings 0/1
Same weights, converted vs openai/gpt-oss-120b. Same weights stored in another dtype (U8/BF16 → MXFP4/BF16), plus 252 new tensors.
Tensors changed: Norms 0/73, Attention 0/288, lm_head 0/1, Embeddings 0/1