--- 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:1452533 - loss:Contrastive base_model: colbert-ir/colbertv2.0 datasets: - redis/langcache-sentencepairs-v1 pipeline_tag: sentence-similarity library_name: PyLate metrics: - accuracy model-index: - name: Fine-tuned ColBERT model for semantic caching results: - task: type: col-berttriplet name: Col BERTTriplet dataset: name: test triplet type: test_triplet metrics: - type: accuracy value: 0.8205713629722595 name: Accuracy --- # 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-v1) 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-v1) - **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-v1-4gpu", ) # 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-v1-4gpu", ) 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, ) ``` ## Evaluation ### Metrics #### Col BERTTriplet * Dataset: `test_triplet` * Evaluated with pylate.evaluation.colbert_triplet.ColBERTTripletEvaluator | Metric | Value | |:-------------|:-----------| | **accuracy** | **0.8206** | ## 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-v1) * Size: 1,452,533 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 | |:-----------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------| | Any Canadian teachers (B.Ed. holders) teaching in U.S. schools? | Any Canadian teachers (B.Ed. holders) teaching in U.S. schools? | Are there many Canadians living and working illegally in the United States? | | Are there any underlying psychological tricks/tactics that are used when designing the lines for rides at amusement parks? | Are there any underlying psychological tricks/tactics that are used when designing the lines for rides at amusement parks? | Is there any tricks for straight lines mcqs? | | Can I pay with a debit card on PayPal? | Can I pay with a debit card on PayPal? | Can you transfer PayPal funds onto a debit card/credit card? | * 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-v1) * Size: 110,066 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 | Do you get more homework in 9th grade than 8th? | * Loss: pylate.losses.contrastive.Contrastive ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 48 - `num_train_epochs`: 5 - `learning_rate`: 0.0002 - `warmup_steps`: 0.1 - `optim`: adamw_torch - `weight_decay`: 0.001 - `eval_strategy`: steps - `per_device_eval_batch_size`: 48 - `eval_on_start`: True - `push_to_hub`: True - `hub_model_id`: aditeyabaral/langcache-colbert-v1-4gpu - `load_best_model_at_end`: True - `ddp_find_unused_parameters`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `per_device_train_batch_size`: 48 - `num_train_epochs`: 5 - `max_steps`: -1 - `learning_rate`: 0.0002 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: None - `warmup_steps`: 0.1 - `optim`: adamw_torch - `optim_args`: None - `weight_decay`: 0.001 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `optim_target_modules`: None - `gradient_accumulation_steps`: 1 - `average_tokens_across_devices`: True - `max_grad_norm`: 1.0 - `label_smoothing_factor`: 0.0 - `bf16`: False - `fp16`: False - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `use_liger_kernel`: False - `liger_kernel_config`: None - `use_cache`: False - `neftune_noise_alpha`: None - `torch_empty_cache_steps`: None - `auto_find_batch_size`: False - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `include_num_input_tokens_seen`: no - `log_level`: passive - `log_level_replica`: warning - `disable_tqdm`: False - `project`: huggingface - `trackio_space_id`: trackio - `eval_strategy`: steps - `per_device_eval_batch_size`: 48 - `prediction_loss_only`: True - `eval_on_start`: True - `eval_do_concat_batches`: True - `eval_use_gather_object`: False - `eval_accumulation_steps`: None - `include_for_metrics`: [] - `batch_eval_metrics`: False - `save_only_model`: False - `save_on_each_node`: False - `enable_jit_checkpoint`: False - `push_to_hub`: True - `hub_private_repo`: None - `hub_model_id`: aditeyabaral/langcache-colbert-v1-4gpu - `hub_strategy`: every_save - `hub_always_push`: False - `hub_revision`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `restore_callback_states_from_checkpoint`: False - `full_determinism`: False - `seed`: 42 - `data_seed`: None - `use_cpu`: False - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `parallelism_config`: None - `dataloader_drop_last`: True - `dataloader_num_workers`: 0 - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `dataloader_prefetch_factor`: None - `remove_unused_columns`: True - `label_names`: None - `train_sampling_strategy`: random - `length_column_name`: length - `ddp_find_unused_parameters`: True - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `ddp_backend`: None - `ddp_timeout`: 1800 - `fsdp`: [] - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `deepspeed`: None - `debug`: [] - `skip_memory_metrics`: True - `do_predict`: False - `resume_from_checkpoint`: None - `warmup_ratio`: None - `local_rank`: -1 - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | Validation Loss | accuracy | |:------:|:-----:|:-------------:|:---------------:|:--------:| | 0 | 0 | - | 1261.8169 | 0.8206 | | 0.1322 | 1000 | 100.6328 | - | - | | 0.2644 | 2000 | 0.6220 | - | - | | 0.3966 | 3000 | 0.5276 | - | - | | 0.5288 | 4000 | 0.7564 | - | - | | 0.6609 | 5000 | 0.5519 | - | - | | 0.7931 | 6000 | 1.8754 | - | - | | 0.9253 | 7000 | 4.2339 | - | - | | 1.0575 | 8000 | 1.8449 | - | - | | 1.1897 | 9000 | 1.6022 | - | - | | 1.3219 | 10000 | 1.4372 | - | - | | 1.4541 | 11000 | 1.2331 | - | - | | 1.5863 | 12000 | 1.1511 | - | - | | 1.7184 | 13000 | 1.0779 | - | - | | 1.8506 | 14000 | 1.0823 | - | - | | 1.9828 | 15000 | 0.9632 | - | - | | 2.1150 | 16000 | 0.8800 | - | - | | 2.2472 | 17000 | 0.8625 | - | - | | 2.3794 | 18000 | 0.8055 | - | - | | 2.5116 | 19000 | 0.6943 | - | - | | 2.6438 | 20000 | 0.7342 | - | - | | 2.7759 | 21000 | 0.7034 | - | - | | 2.9081 | 22000 | 0.6930 | - | - | | 3.0403 | 23000 | 0.6543 | - | - | | 3.1725 | 24000 | 0.6544 | - | - | | 3.3047 | 25000 | 0.5769 | - | - | | 3.4369 | 26000 | 0.5262 | - | - | | 3.5691 | 27000 | 0.5684 | - | - | | 3.7013 | 28000 | 0.5433 | - | - | | 3.8334 | 29000 | 0.5481 | - | - | | 3.9656 | 30000 | 0.5552 | - | - | | 4.0978 | 31000 | 0.5399 | - | - | | 4.2300 | 32000 | 0.5605 | - | - | | 4.3622 | 33000 | 0.5385 | - | - | | 4.4944 | 34000 | 0.4941 | - | - | | 4.6266 | 35000 | 0.5287 | - | - | | 4.7588 | 36000 | 0.5289 | - | - | | 4.8909 | 37000 | 0.5502 | - | - | ### 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}, } ```