--- language: - en license: apache-2.0 tags: - colbert - PyLate - feature-extraction - text-classification - sentence-pair-classification - semantic-similarity - semantic-search - retrieval - reranking - generated_from_trainer - dataset_size:76348209 - loss:Contrastive base_model: colbert-ir/colbertv2.0 datasets: - redis/langcache-sentencepairs-v3 pipeline_tag: sentence-similarity library_name: PyLate --- # Fine-tuned ColBERT model for semantic caching This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [colbert-ir/colbertv2.0](https://huggingface.co/colbert-ir/colbertv2.0) on the [LangCache Sentence Pairs (subsets=['all'], train+val=True)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v3) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. ## Model Details ### Model Description - **Model Type:** PyLate model - **Base model:** [colbert-ir/colbertv2.0](https://huggingface.co/colbert-ir/colbertv2.0) - **Document Length:** 128 tokens - **Query Length:** 128 tokens - **Output Dimensionality:** 128 tokens - **Similarity Function:** MaxSim - **Training Dataset:** - [LangCache Sentence Pairs (subsets=['all'], train+val=True)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v3) - **Language:** en - **License:** apache-2.0 ### Model Sources - **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/) - **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate) - **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate) ### Full Model Architecture ``` ColBERT( (0): Transformer({'max_seq_length': 127, 'do_lower_case': False, 'architecture': 'BertModel'}) (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False}) ) ``` ## Usage First install the PyLate library: ```bash pip install -U pylate ``` ### Retrieval Use this model with PyLate to index and retrieve documents. The index uses [FastPLAID](https://github.com/lightonai/fast-plaid) for efficient similarity search. #### Indexing documents Load the ColBERT model and initialize the PLAID index, then encode and index your documents: ```python from pylate import indexes, models, retrieve # Step 1: Load the ColBERT model model = models.ColBERT( model_name_or_path="aditeyabaral/langcache-colbert-v2", ) # Step 2: Initialize the PLAID index index = indexes.PLAID( index_folder="pylate-index", index_name="index", override=True, # This overwrites the existing index if any ) # Step 3: Encode the documents documents_ids = ["1", "2", "3"] documents = ["document 1 text", "document 2 text", "document 3 text"] documents_embeddings = model.encode( documents, batch_size=32, is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries show_progress_bar=True, ) # Step 4: Add document embeddings to the index by providing embeddings and corresponding ids index.add_documents( documents_ids=documents_ids, documents_embeddings=documents_embeddings, ) ``` Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it: ```python # To load an index, simply instantiate it with the correct folder/name and without overriding it index = indexes.PLAID( index_folder="pylate-index", index_name="index", ) ``` #### Retrieving top-k documents for queries Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores: ```python # Step 1: Initialize the ColBERT retriever retriever = retrieve.ColBERT(index=index) # Step 2: Encode the queries queries_embeddings = model.encode( ["query for document 3", "query for document 1"], batch_size=32, is_query=True, # # Ensure that it is set to False to indicate that these are queries show_progress_bar=True, ) # Step 3: Retrieve top-k documents scores = retriever.retrieve( queries_embeddings=queries_embeddings, k=10, # Retrieve the top 10 matches for each query ) ``` ### Reranking If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank: ```python from pylate import rank, models queries = [ "query A", "query B", ] documents = [ ["document A", "document B"], ["document 1", "document C", "document B"], ] documents_ids = [ [1, 2], [1, 3, 2], ] model = models.ColBERT( model_name_or_path="aditeyabaral/langcache-colbert-v2", ) queries_embeddings = model.encode( queries, is_query=True, ) documents_embeddings = model.encode( documents, is_query=False, ) reranked_documents = rank.rerank( documents_ids=documents_ids, queries_embeddings=queries_embeddings, documents_embeddings=documents_embeddings, ) ``` ## Training Details ### Training Dataset #### LangCache Sentence Pairs (subsets=['all'], train+val=True) * Dataset: [LangCache Sentence Pairs (subsets=['all'], train+val=True)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v3) * Size: 76,348,209 training samples * Columns: anchor, positive, and negative_1 * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative_1 | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative_1 | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------| |
"There aren't many places in Gold Coast where you can find a wide variety of wedding dresses." |
"There aren't many places in Gold Coast where you can find a wide variety of wedding dresses." | Where can I get a wide variety of wedding dresses in Gold Coast? | |
It's easy to say it's good having siblings, but people often suggest it as a universal truth without considering that not everyone enjoys sibling relationships. Having siblings can lead to conflicts, competition, and stress, which might overshadow any potential benefits like companionship or support. Additionally, individual experiences with siblings can vary greatly depending on personality, family dynamics, and cultural background. |
It's easy to say it's good having siblings, but people often suggest it as a universal truth without considering that not everyone enjoys sibling relationships. Having siblings can lead to conflicts, competition, and stress, which might overshadow any potential benefits like companionship or support. Additionally, individual experiences with siblings can vary greatly depending on personality, family dynamics, and cultural background. | What's it like having siblings? | |
To reconcile the idea that 'Education is the Key to Success' with the presence of underemployed graduates and successful criminals, it's important to emphasize that education is one among many factors that contribute to success. Education equips individuals with knowledge, critical thinking skills, and problem-solving abilities, which are essential tools for navigating life's challenges and seizing opportunities. However, success is also influenced by other elements such as personal drive, social connections, opportunities presented, and sometimes sheer luck. Education does not guarantee success on its own; rather, it provides a foundation upon which individuals can build their careers and personal lives. Additionally, the definition of success can be subjective and varies across different cultures and individuals. It's crucial to address practical considerations like ensuring that educational curricula are relevant to the current job market and fostering environments where both hard ... |
To reconcile the idea that 'Education is the Key to Success' with the presence of underemployed graduates and successful criminals, it's important to emphasize that education is one among many factors that contribute to success. Education equips individuals with knowledge, critical thinking skills, and problem-solving abilities, which are essential tools for navigating life's challenges and seizing opportunities. However, success is also influenced by other elements such as personal drive, social connections, opportunities presented, and sometimes sheer luck. Education does not guarantee success on its own; rather, it provides a foundation upon which individuals can build their careers and personal lives. Additionally, the definition of success can be subjective and varies across different cultures and individuals. It's crucial to address practical considerations like ensuring that educational curricula are relevant to the current job market and fostering environments where both hard ... | How do you convince the upcoming generation that "Education is The Key of Success " when we are surrounded by poor graduates and rich criminals? | * Loss: pylate.losses.contrastive.Contrastive ### Evaluation Dataset #### LangCache Sentence Pairs (split=test) * Dataset: [LangCache Sentence Pairs (split=test)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v3) * Size: 132,354 evaluation samples * Columns: anchor, positive, and negative_1 * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative_1 | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative_1 | |:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------| | What high potential jobs are there other than computer science? | What high potential jobs are there other than computer science? | Why IT or Computer Science jobs are being over rated than other Engineering jobs? | | Would India ever be able to develop a missile system like S300 or S400 missile? | Would India ever be able to develop a missile system like S300 or S400 missile? | Should India buy the Russian S400 air defence missile system? | | water from the faucet is being drunk by a yellow dog | A yellow dog is drinking water from the faucet | Childlessness is low in Eastern European countries. | * Loss: pylate.losses.contrastive.Contrastive ### Framework Versions - Python: 3.12.12 - Sentence Transformers: 5.3.0 - PyLate: 1.5.0 - Transformers: 5.3.0 - PyTorch: 2.9.0+cu130 - Accelerate: 1.13.0 - Datasets: 4.8.5 - Tokenizers: 0.22.2 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084" } ``` #### PyLate ```bibtex @inproceedings{DBLP:conf/cikm/ChaffinS25, author = {Antoine Chaffin and Rapha{"{e}}l Sourty}, editor = {Meeyoung Cha and Chanyoung Park and Noseong Park and Carl Yang and Senjuti Basu Roy and Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {PyLate: Flexible Training and Retrieval for Late Interaction Models}, booktitle = {Proceedings of the 34th {ACM} International Conference on Information and Knowledge Management, {CIKM} 2025, Seoul, Republic of Korea, November 10-14, 2025}, pages = {6334--6339}, publisher = {{ACM}}, year = {2025}, url = {https://github.com/lightonai/pylate}, doi = {10.1145/3746252.3761608}, } ```