sentence-transformers
ONNX
Safetensors
English
bert
ColBERT
multi-vector
RAGatouille
passage-retrieval
Instructions to use answerdotai/answerai-colbert-small-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use answerdotai/answerai-colbert-small-v1 with sentence-transformers:
from sentence_transformers import MultiVectorEncoder model = MultiVectorEncoder("answerdotai/answerai-colbert-small-v1") queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Notebooks
- Google Colab
- Kaggle
Ollama compatability
#13
by twine-network - opened
Is it possible to make a GGUF version of this model to use with Ollama? I haven't been able to find a tool or workflow for this. Wondering if it is even possible.
Not sure if ollama supports colbert-style models?
Ollama docs:
Coming soon
More features are coming to support workflows that involve embeddings:
Batch embeddings: processing multiple input data prompts simultaneously
OpenAI API Compatibility: support for the /v1/embeddings OpenAI-compatible endpoint
More embedding model architectures: support for ColBERT, RoBERTa, and other embedding model architectures
Oh nice. I had just come across your infinity project a few days ago and had it sitting in an open tab to look at when I got a minute. That just got bumped up the todo list. Thanks