jinaai/jina-code-embeddings-1.5b
Full fine-tune vs Qwen/Qwen2.5-Coder-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
2 derivatives checked
- jinaai/jina-code-embeddings-1.5b-GGUF: Same weights, converted
- RESMP-DEV/jina-code-embeddings-1.5b-mxfp4-block-gptq: Quantization
1 other repos hold byte-for-byte identical weight files.