RTannous/gpt-oss-20b-multilingual-reasoner

Same weights, converted vs unsloth/gpt-oss-20b. Same weights stored in another dtype (U8/BF16 → BF16/F32), plus 48 new tensors.

Tensors changed: Norms 0/49, MLP 0/96, Attention 0/216, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse