sparse-encoder/splade-camembert-base-v2
Full fine-tune vs almanach/camembert-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: lm_head 5/5, Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/48
Full fine-tune vs almanach/camembert-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: lm_head 5/5, Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/48