jinaai/jina-embeddings-v5-text-nano
Full fine-tune vs EuroBERT/EuroBERT-210m. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 1/1, Norms 25/25, MLP 36/36, Attention 48/48
13 derivatives checked
- jinaai/jina-embeddings-v5-text-nano-retrieval: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-classification: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-retrieval-GGUF: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-text-matching: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-clustering: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-text-matching-GGUF: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-classification-GGUF: LoRA-style
- jinaai/jina-embeddings-v5-text-nano-clustering-GGUF: LoRA-style
- cstr/jina-v5-nano-GGUF: Full fine-tune
- jinaai/jina-embeddings-v5-text-nano-mlx: Same weights, repacked
- noname002/jina-text-matching-embeddings-v5-text-nano-retrieval-mc4-3fre-v3: LoRA-style
- noname002/jina-embeddings-v5-text-nano-retrieval-df-bkainews: LoRA-style
- noname002/jina-embeddings-v5-text-nano-retrieval-df-3fre-mc4-80k: LoRA-style