tatsuyaaaaaaa/GPT-OSS-Swallow-20B-RL-v0.1-gguf

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

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

On the Hub · Downloads on Model Pulse