gartland/finewebedu-49K-450M-seed42
Different architecture vs allenai/OLMo-7B-0724-hf. Different architecture: only 0 of 226/192 tensors match by name and shape.
Different architecture vs allenai/OLMo-7B-0724-hf. Different architecture: only 0 of 226/192 tensors match by name and shape.