antoinelouis/colbertv1-camembert-base-mmarcoFR

Full fine-tune vs almanach/camembert-base. Fine-tune: 99% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/50

1 derivatives checked

On the Hub · Downloads on Model Pulse