Aiden1020/LocalSubs-EN-ZH-TW-0.6B

Full fine-tune vs NiuTrans/LMT-60-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 104/113, MLP 84/84, Attention 112/112

On the Hub · Downloads on Model Pulse