unsloth/gpt-oss-120b-BF16

Same weights, repacked vs openai/gpt-oss-120b. Same weights in different files (re-saved, re-sharded or new metadata), plus 72 new tensors.

Tensors changed: MLP 0/144, Norms 0/73, Attention 0/324, lm_head 0/1, Embeddings 0/1

5 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse