burnedinthesky/gpt2-olmo2-1b-warm120-ot-muon-lr4e-3-tok401k-seq1024-cos-wu5-485335

Different architecture vs allenai/OLMo-2-0425-1B. Different architecture: only 0 of 179/148 tensors match by name and shape.

On the Hub · Downloads on Model Pulse