ayushexel/colbert-answerai-colbert-small-v1-1-neg-1-epoch-gooaq-1995000

PyLate model based on answerdotai/answerai-colbert-small-v1

This is a PyLate model finetuned from answerdotai/answerai-colbert-small-v1. It maps sentences & paragraphs to sequences of 96-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: answerdotai/answerai-colbert-small-v1 <!-- at revision be1703c55532145a844da800eea4c9a692d7e267 -->
• —Document Length: 300 tokens
• —Query Length: 32 tokens
• —Output Dimensionality: 96 tokens
• —Similarity Function: MaxSim <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown -->

Model Sources

• —Documentation: PyLate Documentation
• —Repository: PyLate on GitHub
• —Hugging Face: PyLate models on Hugging Face

Full Model Architecture

ColBERT(
  (0): Transformer({'max_seq_length': 31, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Dense({'in_features': 384, 'out_features': 96, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
)

Usage

First install the PyLate library:

pip install -U pylate

Retrieval

PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval.

Indexing documents

First, load the ColBERT model and initialize the Voyager index, then encode and index your documents:

from pylate import indexes, models, retrieve

# Step 1: Load the ColBERT model
model = models.ColBERT(
    model_name_or_path=ayushexel/colbert-answerai-colbert-small-v1-1-neg-1-epoch-gooaq-1995000,
)

# Step 2: Initialize the Voyager index
index = indexes.Voyager(
    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:

# To load an index, simply instantiate it with the correct folder/name and without overriding it
index = indexes.Voyager(
    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:

# 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:

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=ayushexel/colbert-answerai-colbert-small-v1-1-neg-1-epoch-gooaq-1995000,
)

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,
)

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

Evaluation

Metrics

Col BERTTriplet

• —Evaluated with <code>pylate.evaluation.colbert_triplet.ColBERTTripletEvaluator</code>

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

Training Dataset

Unnamed Dataset

• —Size: 1,893,947 training samples
• —Columns: <code>question</code>, <code>answer</code>, and <code>negative</code>
• —Approximate statistics based on the first 1000 samples: | | question | answer | negative | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 9 tokens</li><li>mean: 12.91 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 16 tokens</li><li>mean: 31.72 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 31.75 tokens</li><li>max: 32 tokens</li></ul> |
• —Samples: | question | answer | negative | |:----------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>what are girl names that start with g?</code> | <code>['Grace. Grace is one of those classic girl names that never seems to go out of style. ... ', 'Gabriella. Hebrew Origin. ... ', 'Gabrielle. French Origin. ... ', 'Genevieve. French: White wave. ... ', 'Giselle. French: Pledge. ... ', 'Gloria. Latin: Glory, renown, and respect. ... ', 'Gina. English: Abbreviation of names ending in "gina" ... ', 'Gabriela.']</code> | <code>| Report abuse. gn is for grains, g is grams. If you are using this scale for reloading make sure it is set to gn.</code> | | <code>is wheat healthier than white bread?</code> | <code>Whole wheat is processed to include all three nutritious parts, but white flour uses only the endosperm. When put head-to-head with whole wheat bread, white is a nutritional lightweight. Whole wheat is much higher in fiber, vitamins B6 and E, magnesium, zinc, folic acid and chromium.</code> | <code>Very Strong White. Made from a blend of premium wheat, Allinson Very Strong White Bread Flour has a higher protein content and gluten strength than our strong flour. ... You can use this flour whenever your recipes call for strong white bread flour and it will produce a higher rise and a better texture.</code> | | <code>are the mtv vmas live?</code> | <code>The annual VMA ceremony occurs before the end of summer and held either in late August or mid-September, and broadcast live on MTV, along with a "roadblock" simulcast across MTV's sister networks since 2014, which is utilized to maximize the ceremony's ratings.</code> | <code>TIL MTV and VH1 were always a part of the same company and are in fact SISTER CHANNELS. Viacom is huge, they also own Comedy Central. Viacom bought MTV, VH1, BET, Nickelodeon (MTV Networks) and Showtime from Warner in 1985.</code> |
• —Loss: <code>pylate.losses.contrastive.Contrastive</code>

Evaluation Dataset

Unnamed Dataset

• —Size: 5,000 evaluation samples
• —Columns: <code>question</code>, <code>answer</code>, and <code>negative_1</code>
• —Approximate statistics based on the first 1000 samples: | | question | answer | negative_1 | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 9 tokens</li><li>mean: 12.89 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 31.76 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 31.41 tokens</li><li>max: 32 tokens</li></ul> |
• —Samples: | question | answer | negative_1 | |:----------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>what season and episode does jon snow come back to life?</code> | <code>This is the mother of all Game of Thrones spoilers, so if you haven't watched season 6 episode 2 yet, please click away now. Jon Snow is alive.</code> | <code>Then, of course, there is Jon Snow's resurrection in Episode 2 of Season 6, an event that changed everything about Thrones.</code> | | <code>do the rich get richer?</code> | <code>It's true, the rich do get richer—here's why... ... The growing wealth of the rich, and the relative stagnation of the middle class, are due in large part to diverging incomes, but investments also play an increasingly important role. And it's not just that the wealthy have more investments.</code> | <code>It's true, the rich do get richer—here's why... ... The growing wealth of the rich, and the relative stagnation of the middle class, are due in large part to diverging incomes, but investments also play an increasingly important role. And it's not just that the wealthy have more investments.</code> | | <code>how long can you eat leftover lamb?</code> | <code>Store it safely You can safely store cooked lamb for up to three days in the fridge, or for up to two months in the freezer. Make sure it's fully defrosted before using and, if it's been frozen once, don't re-freeze.</code> | <code>Lamb. ... The meat of sheep 6 to 10 weeks old is usually sold as baby lamb, and spring lamb is from sheep of five to six months.</code> |
• —Loss: <code>pylate.losses.contrastive.Contrastive</code>

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —per_device_train_batch_size: 128
• —per_device_eval_batch_size: 128
• —learning_rate: 3e-06
• —num_train_epochs: 1
• —warmup_ratio: 0.1
• —seed: 12
• —bf16: True
• —dataloader_num_workers: 12
• —load_best_model_at_end: True

All Hyperparameters

<details><summary>Click to expand</summary>

• —overwrite_output_dir: False
• —do_predict: False
• —eval_strategy: steps
• —prediction_loss_only: True
• —per_device_train_batch_size: 128
• —per_device_eval_batch_size: 128
• —per_gpu_train_batch_size: None
• —per_gpu_eval_batch_size: None
• —gradient_accumulation_steps: 1
• —eval_accumulation_steps: None
• —torch_empty_cache_steps: None
• —learning_rate: 3e-06
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —max_grad_norm: 1.0
• —num_train_epochs: 1
• —max_steps: -1
• —lr_scheduler_type: linear
• —lr_scheduler_kwargs: {}
• —warmup_ratio: 0.1
• —warmup_steps: 0
• —log_level: passive
• —log_level_replica: warning
• —log_on_each_node: True
• —logging_nan_inf_filter: True
• —save_safetensors: True
• —save_on_each_node: False
• —save_only_model: False
• —restore_callback_states_from_checkpoint: False
• —no_cuda: False
• —use_cpu: False
• —use_mps_device: False
• —seed: 12
• —data_seed: None
• —jit_mode_eval: False
• —use_ipex: False
• —bf16: True
• —fp16: False
• —fp16_opt_level: O1
• —half_precision_backend: auto
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: None
• —local_rank: 0
• —ddp_backend: None
• —tpu_num_cores: None
• —tpu_metrics_debug: False
• —debug: []
• —dataloader_drop_last: False
• —dataloader_num_workers: 12
• —dataloader_prefetch_factor: None
• —past_index: -1
• —disable_tqdm: False
• —remove_unused_columns: True
• —label_names: None
• —load_best_model_at_end: True
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —deepspeed: None
• —label_smoothing_factor: 0.0
• —optim: adamw_torch
• —optim_args: None
• —adafactor: False
• —group_by_length: False
• —length_column_name: length
• —ddp_find_unused_parameters: None
• —ddp_bucket_cap_mb: None
• —ddp_broadcast_buffers: False
• —dataloader_pin_memory: True
• —dataloader_persistent_workers: False
• —skip_memory_metrics: True
• —use_legacy_prediction_loop: False
• —push_to_hub: False
• —resume_from_checkpoint: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_private_repo: None
• —hub_always_push: False
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —include_inputs_for_metrics: False
• —include_for_metrics: []
• —eval_do_concat_batches: True
• —fp16_backend: auto
• —push_to_hub_model_id: None
• —push_to_hub_organization: None
• —mp_parameters:
• —auto_find_batch_size: False
• —full_determinism: False
• —torchdynamo: None
• —ray_scope: last
• —ddp_timeout: 1800
• —torch_compile: False
• —torch_compile_backend: None
• —torch_compile_mode: None
• —dispatch_batches: None
• —split_batches: None
• —include_tokens_per_second: False
• —include_num_input_tokens_seen: False
• —neftune_noise_alpha: None
• —optim_target_modules: None
• —batch_eval_metrics: False
• —eval_on_start: False
• —use_liger_kernel: False
• —eval_use_gather_object: False
• —average_tokens_across_devices: False
• —prompts: None
• —batch_sampler: batch_sampler
• —multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• —Python: 3.11.0
• —Sentence Transformers: 4.0.1
• —PyLate: 1.1.7
• —Transformers: 4.48.2
• —PyTorch: 2.6.0+cu124
• —Accelerate: 1.6.0
• —Datasets: 3.5.0
• —Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@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

@misc{PyLate,
title={PyLate: Flexible Training and Retrieval for Late Interaction Models},
author={Chaffin, Antoine and Sourty, Raphaël},
url={https://github.com/lightonai/pylate},
year={2024}
}

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->