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-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TomoroAI/tomoro-colqwen3-embed-4b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TomoroAI/tomoro-colqwen3-embed-4b", trust_remote_code=True, device_map="auto") - sentence-transformers
How to use TomoroAI/tomoro-colqwen3-embed-4b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TomoroAI/tomoro-colqwen3-embed-4b", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - ColPali
How to use TomoroAI/tomoro-colqwen3-embed-4b 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
Remove convert_to_tensor=True in MultiVectorEncoder, this parameter was removed
#6
by tomaarsen HF Staff - opened
README.md
CHANGED
|
@@ -180,8 +180,8 @@ documents = [
|
|
| 180 |
for i in range(1, 5)
|
| 181 |
]
|
| 182 |
|
| 183 |
-
query_embeddings = model.encode_query(queries
|
| 184 |
-
document_embeddings = model.encode_document(documents
|
| 185 |
print(f"Query 0 shape: {tuple(query_embeddings[0].shape)}")
|
| 186 |
print(f"Document 0 shape: {tuple(document_embeddings[0].shape)}")
|
| 187 |
# Query 0 shape: (23, 320)
|
|
|
|
| 180 |
for i in range(1, 5)
|
| 181 |
]
|
| 182 |
|
| 183 |
+
query_embeddings = model.encode_query(queries)
|
| 184 |
+
document_embeddings = model.encode_document(documents)
|
| 185 |
print(f"Query 0 shape: {tuple(query_embeddings[0].shape)}")
|
| 186 |
print(f"Document 0 shape: {tuple(document_embeddings[0].shape)}")
|
| 187 |
# Query 0 shape: (23, 320)
|