NostraEmpire/mirror-olmo-2-13b-instruct

Full fine-tune vs allenai/OLMo-2-1124-13B-Instruct-RLVR2. Fine-tune: 96% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, MLP 120/120, Norms 158/161, Attention 160/160, lm_head 1/1

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse