mradermacher/Olmo-3-7B-RL-Zero-Math-Code-GGUF

Same weights, converted vs pmahdavi/Olmo-3-7B-RL-Zero-Math-Code. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/96, Norms 0/129, Attention 0/128

On the Hub · Downloads on Model Pulse