gartland/finewebedu-98K-lr1.2e-3-seed42
Different architecture vs allenai/OLMo-7B-0724-hf. Different architecture: only 0 of 226/111 tensors match by name and shape.
Different architecture vs allenai/OLMo-7B-0724-hf. Different architecture: only 0 of 226/111 tensors match by name and shape.