bartowski/p-e-w_gpt-oss-20b-heretic-GGUF

Same weights, converted vs p-e-w/gpt-oss-20b-heretic. Same weights stored in another dtype (BF16 → BF16/F32), plus 168 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse