amDANIEL2024/tulati-v1-afrie5-salt
Partial fine-tune vs McGill-NLP/AfriE5-Large-instruct. Partial change: 54% of the weights changed (attention, embeddings, other), in 24 of 24 layers.
Tensors changed: Embeddings 1/3, Attention 192/192, other 96/98
Partial fine-tune vs McGill-NLP/AfriE5-Large-instruct. Partial change: 54% of the weights changed (attention, embeddings, other), in 24 of 24 layers.
Tensors changed: Embeddings 1/3, Attention 192/192, other 96/98