McGill-NLP/AfriE5-Large-instruct
Partial fine-tune vs intfloat/multilingual-e5-large-instruct. Partial change: 54% of the weights changed (attention, embeddings, norms, other), in 24 of 24 layers.
Tensors changed: Embeddings 2/5, Norms 51/96, Attention 191/192, other 96/98
2 derivatives checked
- mradermacher/AfriE5-Large-instruct-GGUF: Same weights, converted
- amDANIEL2024/tulati-v1-afrie5-salt: Partial fine-tune