Add model card for jina-v5-small GGUF

README.md

@@ -0,0 +1,76 @@
+---
+license: cc-by-nc-4.0
+language: [multilingual]
+tags: [embeddings, gguf, ggml, text-embeddings, qwen3, crispembed]
+pipeline_tag: feature-extraction
+base_model: jinaai/jina-embeddings-v5-small
+---
+
+# jina-v5-small GGUF
+
+GGUF format of [jinaai/jina-embeddings-v5-small](https://huggingface.co/jinaai/jina-embeddings-v5-small) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed).
+
+Jina Embeddings v5 Small. Full-size decoder model, 1024-dimensional.
+
+## Files
+
+| File | Quantization | Size |
+|------|-------------|------|
+| [jina-v5-small-q8_0.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small-q8_0.gguf) | Q8_0 | 609 MB |
+| [jina-v5-small.gguf](https://huggingface.co/cstr/jina-v5-small-GGUF/resolve/main/jina-v5-small.gguf) | F32 | 2279 MB |
+
+
+## Quick Start
+
+```bash
+# Download
+huggingface-cli download cstr/jina-v5-small-GGUF jina-v5-small-q8_0.gguf --local-dir .
+
+# Run with CrispEmbed
+./crispembed -m jina-v5-small-q8_0.gguf "Hello world"
+
+# Or with auto-download
+./crispembed -m jina-v5-small "Hello world"
+```
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Architecture | Qwen3 |
+| Parameters | 600M |
+| Embedding Dimension | 1024 |
+| Layers | 28 |
+| Pooling | last-token |
+| Tokenizer | GPT-2 BPE |
+| Base Model | [jinaai/jina-embeddings-v5-small](https://huggingface.co/jinaai/jina-embeddings-v5-small) |
+
+## Verification
+
+Verified bit-identical to HuggingFace sentence-transformers (cosine similarity >= 0.999 on test texts).
+
+## Usage with CrispEmbed
+
+CrispEmbed is a lightweight C/C++ text embedding inference engine using ggml.
+No Python runtime, no ONNX. Supports BERT, XLM-R, Qwen3, and Gemma3 architectures.
+
+```bash
+# Build CrispEmbed
+git clone https://github.com/CrispStrobe/CrispEmbed
+cd CrispEmbed
+cmake -S . -B build && cmake --build build -j
+
+# Encode
+./build/crispembed -m jina-v5-small-q8_0.gguf "query text"
+
+# Server mode
+./build/crispembed-server -m jina-v5-small-q8_0.gguf --port 8080
+curl -X POST http://localhost:8080/v1/embeddings \
+    -d '{"input": ["Hello world"], "model": "jina-v5-small"}'
+```
+
+## Credits
+
+- Original model: [jinaai/jina-embeddings-v5-small](https://huggingface.co/jinaai/jina-embeddings-v5-small)
+- Inference engine: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (ggml-based)
+- Conversion: `convert-decoder-embed-to-gguf.py`