lewtun/tailsft-repro-olmo2-1b-std

Partial fine-tune vs allenai/OLMo-2-0425-1B. Partial change: 86% of the weights changed (attention, lm_head, mlp, norms), in 16 of 16 layers.

Tensors changed: Embeddings 0/1, MLP 48/48, Norms 50/65, Attention 64/64, lm_head 1/1

On the Hub · Downloads on Model Pulse