Tamil-ai/tamil-embed-base

Full fine-tune vs intfloat/multilingual-e5-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 3/3, Attention 96/96, other 48/50

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

On the Hub · Downloads on Model Pulse