sashisuseso/GPT-OSS-Swallow-20B-SFT-v0.1-GGUF

Same weights, converted vs tokyotech-llm/GPT-OSS-Swallow-20B-SFT-v0.1. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.

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

On the Hub · Downloads on Model Pulse