contextboxai/halong_embedding
Partial fine-tune vs intfloat/multilingual-e5-base. Partial change: 31% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/50
3 derivatives checked
- truro7/vn-law-embedding: Partial fine-tune
- doof-ferb/halong-embedding-gguf: Same weights, converted
- minhthuan77f1/medical_embedding_vietnamese: Partial fine-tune
3 other repos hold byte-for-byte identical weight files.