jinaai/jina-embeddings-v5-text-small
Full fine-tune vs Qwen/Qwen3-0.6B-Base. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 113/113, MLP 84/84, Attention 112/112
11 derivatives checked
- jinaai/jina-embeddings-v5-text-small-retrieval: LoRA-style
- jinaai/jina-embeddings-v5-text-small-text-matching: LoRA-style
- jinaai/jina-embeddings-v5-text-small-classification: LoRA-style
- jinaai/jina-embeddings-v5-text-small-clustering: LoRA-style
- jinaai/jina-embeddings-v5-text-small-retrieval-GGUF: LoRA-style
- jinaai/jina-embeddings-v5-text-small-clustering-GGUF: LoRA-style
- jinaai/jina-embeddings-v5-text-small-classification-GGUF: LoRA-style
- jinaai/jina-embeddings-v5-text-small-text-matching-GGUF: LoRA-style
- cstr/jina-v5-small-GGUF: Full fine-tune
- thanhtan2136/jina-embeddings-v5-text-small-text-matching: LoRA-style
- jinaai/jina-embeddings-v5-text-small-mlx: Same weights, repacked