mradermacher/gpt-oss-2.5B-A1.3B-GGUF

Same weights, converted vs inference-optimization/gpt-oss-2.5B-A1.3B. Same weights stored in another dtype (BF16 → F16/F32), plus 42 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/13, MLP 0/12, Attention 0/48

On the Hub · Downloads on Model Pulse