RedaAlami/Falcon3-7B-Instruct-Distill-DS-v1
Full fine-tune vs tiiuae/Falcon3-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 46/57, MLP 84/84, Attention 112/112, lm_head 1/1
Full fine-tune vs tiiuae/Falcon3-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 46/57, MLP 84/84, Attention 112/112, lm_head 1/1