Views
No views yet
| File | Quantization | Size |
|---|---|---|
| arctic-embed-xs-f32.gguf | F32 | 0 MB |
| arctic-embed-xs-q4_k.gguf | Q4_K | 0 MB |
| arctic-embed-xs-q8_0.gguf | Q8_0 | 0 MB |
| arctic-embed-xs.gguf | F32 | 0 MB |
1./crispembed -m arctic-embed-xs "Hello world"
2./crispembed-server -m arctic-embed-xs --port 80801# Create model
2echo "FROM arctic-embed-xs-q8_0.gguf" > Modelfile
3ollama create arctic-embed-xs -f Modelfile
4
5# Embed
6curl http://localhost:11434/api/embed -d '{"model":"arctic-embed-xs","input":["Hello world"]}'1from crispembed import CrispEmbed
2model = CrispEmbed("arctic-embed-xs-q8_0.gguf")
3vectors = model.encode(["Hello world", "Goodbye world"])| Property | Value |
|---|---|
| Architecture | BERT |
| Parameters | 22M |
| Embedding Dimension | 384 |
| Layers | 6 |
| Pooling | CLS |
| Tokenizer | WordPiece |
| Language | en |
| Q8_0 vs HuggingFace | 0.9999 |
| Q4_K vs HuggingFace | 0.995 |
POST /embed — nativePOST /v1/embeddings — OpenAI-compatiblePOST /api/embed — Ollama-compatiblePOST /api/embeddings — Ollama legacySnowflake.mit. This repository redistributes under the same terms; it grants no rights the upstream licence does not.