mradermacher/RLVR-8B-0926-GGUF

Same weights, converted vs stepfun-ai/RLVR-8B-0926. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse