Visual Document Retrieval
Transformers
Safetensors
sentence-transformers
ColPali
multilingual
colqwen3
feature-extraction
multi-vector
text
image
video
multimodal-embedding
vidore
multilingual-embedding
custom_code
Instructions to use TomoroAI/tomoro-colqwen3-embed-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TomoroAI/tomoro-colqwen3-embed-8b with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TomoroAI/tomoro-colqwen3-embed-8b", trust_remote_code=True, device_map="auto") - sentence-transformers
How to use TomoroAI/tomoro-colqwen3-embed-8b with sentence-transformers:
from sentence_transformers import MultiVectorEncoder model = MultiVectorEncoder("TomoroAI/tomoro-colqwen3-embed-8b", trust_remote_code=True) 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) - ColPali
How to use TomoroAI/tomoro-colqwen3-embed-8b with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
-
Remove convert_to_tensor=True in MultiVectorEncoder, this parameter was removed (#3)
- Remove convert_to_tensor=True in MultiVectorEncoder, this parameter was removed (51408ecefb6689bf239f0bd77096323face41c70) Co-authored-by: Tom Aarsen <tomaarsen@users.noreply.huggingface.co>7901e21
-
Complete Transformers 5.x multimodal and save support (#2)
- Complete Transformers 5.x multimodal and save support (c27010395083d85570830cd469c545e582b33076) - Fix Transformers 5 tied-weight save mapping (6030c5ce87f00639f2d8e3461954bbaacdb3a0eb)0d4e76e -
Fix transformers 5.x loading and add Sentence Transformers support (#1)
- Fix transformers 5.x loading and add Sentence Transformers support (ee94a5287c2b48716f93763594be7bcf18529252) Co-authored-by: Tom Aarsen <tomaarsen@users.noreply.huggingface.co>f28f441
-
Update README.md
Verified signature4965843 -
Update Prerequisites
Verified signature02e7867
-
Update MMEB-v2 video_ret evaluations
Verified signatureaed92f6
-
Updated zero-shot performance of CareBench
Verified signatureb0165a8 -
Update README.md
Verified signature3073d1d -
Update video processor max pixels
Verified signaturef447b01 -
Video retrieval example fix
Verified signaturec671e8c
-
Update README.md
Verified signature6138a84 -
Update results of video retrieval benchmark: CareBench
Verified signature8dd643f -
Update configuration logic for supporting any to any batch retrieval
Verified signature0b9fe28 -
Update configuration logic for supporting any to any batch retrieval
Verified signature091b5b5
-
Update README.md
Verified signature5ba6fea
-
Update README.md
Verified signature7c8f37d -
Update README.md
Verified signaturec37df5a -
Update README.md
Verified signatureba505d5 -
Update README.md
Verified signature0b75f48 -
Update README.md
Verified signature5af752d -
Update README.md
Verified signature83f3273 -
Update README.md
Verified signatured82579d -
Update README.md
Verified signature374d9f6 -
Update README.md
Verified signaturea24ba92 -
Update README.md
Verified signature3e4686a -
Add README
Verified signature4845a4f -
Upload checkpoint
Verified signature5a4159a -
initial commit
Verified signaturea9d4f11