This is a PyLate model finetuned from answerdotai/ModernBERT-base on the msmarco-10m-triplets 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: answerdotai/ModernBERT-base
Document Length: 512 tokens
Query Length: 32 tokens
Output Dimensionality: 128 tokens
Similarity Function: MaxSim
Training Dataset:
- msmarco-10m-triplets

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': 512, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (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:

pip install -U pylate

Retrieval

Use this model with PyLate to index and retrieve documents. The index uses FastPLAID 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="pylate_model_id",
)

# 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="pylate_model_id",
)

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

Py Late Information Retrieval

Dataset: ['NanoClimateFEVER', 'NanoDBPedia', 'NanoFEVER', 'NanoFiQA2018', 'NanoHotpotQA', 'NanoMSMARCO', 'NanoNFCorpus', 'NanoNQ', 'NanoQuoraRetrieval', 'NanoSCIDOCS', 'NanoArguAna', 'NanoSciFact', 'NanoTouche2020']
Evaluated with pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
MaxSim_accuracy@1	0.28	0.72	0.86	0.54	0.86	0.48	0.46	0.48	0.98	0.42	0.14	0.7	0.7347
MaxSim_accuracy@3	0.5	0.92	0.98	0.68	0.94	0.66	0.56	0.72	1.0	0.62	0.44	0.82	0.9388
MaxSim_accuracy@5	0.56	0.94	1.0	0.72	0.98	0.76	0.56	0.78	1.0	0.7	0.6	0.82	0.9796
MaxSim_accuracy@10	0.68	0.98	1.0	0.8	0.98	0.84	0.6	0.9	1.0	0.78	0.8	0.86	1.0
MaxSim_precision@1	0.28	0.72	0.86	0.54	0.86	0.48	0.46	0.48	0.98	0.42	0.14	0.7	0.7347
MaxSim_precision@3	0.1733	0.6333	0.3333	0.3133	0.4933	0.22	0.38	0.24	0.4	0.3267	0.1467	0.2867	0.6803
MaxSim_precision@5	0.128	0.576	0.208	0.224	0.312	0.152	0.312	0.164	0.26	0.272	0.12	0.184	0.6204
MaxSim_precision@10	0.088	0.516	0.104	0.136	0.168	0.084	0.25	0.096	0.136	0.164	0.08	0.096	0.5367
MaxSim_recall@1	0.1317	0.0865	0.8067	0.3187	0.43	0.48	0.0439	0.44	0.8573	0.0897	0.14	0.675	0.052
MaxSim_recall@3	0.2267	0.1788	0.9267	0.4837	0.74	0.66	0.0779	0.66	0.9487	0.2017	0.44	0.8	0.1368
MaxSim_recall@5	0.2667	0.2473	0.9567	0.5449	0.78	0.76	0.0907	0.74	0.9793	0.2797	0.6	0.82	0.2049
MaxSim_recall@10	0.3417	0.3664	0.9567	0.6157	0.84	0.84	0.1133	0.86	0.9933	0.3357	0.8	0.85	0.3416
MaxSim_ndcg@10	0.2943	0.6345	0.9068	0.5508	0.7954	0.6514	0.3198	0.6539	0.9772	0.3438	0.4479	0.7809	0.5988
MaxSim_mrr@10	0.4137	0.819	0.9207	0.6249	0.899	0.5919	0.5087	0.6133	0.99	0.5464	0.3378	0.7615	0.8459
MaxSim_map@100	0.2304	0.4728	0.8768	0.4878	0.7288	0.6011	0.1411	0.581	0.9632	0.2646	0.3445	0.7573	0.4257

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator

Metric	Value
MaxSim_accuracy@1	0.5888
MaxSim_accuracy@3	0.7522
MaxSim_accuracy@5	0.8
MaxSim_accuracy@10	0.8631
MaxSim_precision@1	0.5888
MaxSim_precision@3	0.3559
MaxSim_precision@5	0.2717
MaxSim_precision@10	0.1888
MaxSim_recall@1	0.3501
MaxSim_recall@3	0.4985
MaxSim_recall@5	0.5592
MaxSim_recall@10	0.6349
MaxSim_ndcg@10	0.612
MaxSim_mrr@10	0.6825
MaxSim_map@100	0.5289

Training Details

Training Dataset

msmarco-10m-triplets

Dataset: msmarco-10m-triplets at 8c5139a
Size: 10,000,000 training samples
Columns: query, positive, and negative
Approximate statistics based on the first 1000 samples:
query positive negative
type string string string
details
min: 4 tokens
mean: 9.31 tokens
max: 31 tokens
min: 20 tokens
mean: 31.95 tokens
max: 32 tokens
min: 18 tokens
mean: 31.91 tokens
max: 32 tokens

Samples:

query	positive	negative
`the most important factor that influences k+ secretion is __________.`	`The regulation of K+ distribution between the intracellular and extracellular space is referred to as internal K+ balance. The most important factors regulating this movement under normal conditions are insulin and catecholamines (1).`	`They are both also important for secretion and flow of bile: 1 Cholecystokinin: The name of this hormone describes its effect on the biliary system-cholecysto = gallbladder and kinin = movement. 2 Secretin: This hormone is secreted in response to acid in the duodenum.`
`how much did the mackinac bridge cost to build`	`The cost to design the project was $3,500,000 (Steinman Company). The cost to construct the bridge was $70, 268,500. Two primary contractors were hired to build the bridge: American Bridge for superstructure - $44,532,900; and Merritt-Chapman and Scott of New York for the foundations - $25,735,600.`	`When your child needs a dental tooth bridge, you need to know the average cost so you can factor the price into your budget. Several factors affect the price of a bridge, which can run between $700 to $1,500 per tooth. If you have insurance or your child is covered by Medicaid, part of the cost may be covered.`
`when do concussion symptoms appear`	`Then you can get advice on what to do next. For milder symptoms, the doctor may recommend rest and ask you to watch your child closely for changes, such as a headache that gets worse. Symptoms of a concussion don't always show up right away, and can develop within 24 to 72 hours after an injury.`	`Concussion: A traumatic injury to soft tissue, usually the brain, as a result of a violent blow, shaking, or spinning. A brain concussion can cause immediate but temporary impairment of brain functions, such as thinking, vision, equilibrium, and consciousness. After a person has had a concussion, he or she is at increased risk for recurrence. Moreover, after a person has several concussions, less of a blow can cause injury, and the person can require more time to recover.`

Loss: pylate.losses.contrastive.Contrastive

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 64
learning_rate: 3e-05
max_steps: 50000
fp16: True
dataloader_drop_last: True
dataloader_num_workers: 8
ddp_find_unused_parameters: False
torch_compile: True
torch_compile_backend: inductor
eval_on_start: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 64
per_device_eval_batch_size: 8
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-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3.0
max_steps: 50000
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
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: True
dataloader_num_workers: 8
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
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
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: False
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
hub_revision: None
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: True
torch_compile_backend: inductor
torch_compile_mode: 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: True
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

	query	positive	negative
type	string	string	string
details	min: 4 tokens mean: 9.31 tokens max: 31 tokens	min: 20 tokens mean: 31.95 tokens max: 32 tokens	min: 18 tokens mean: 31.91 tokens max: 32 tokens

xtr-replicability/modernbert_xtr_contrastive_k128

PyLate model based on answerdotai/ModernBERT-base

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Retrieval

Indexing documents

Retrieving top-k documents for queries

Reranking

Evaluation

Metrics

Py Late Information Retrieval

Nano BEIR

Training Details

Training Dataset

msmarco-10m-triplets

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

xtr-replicability/
modernbert_xtr_contrastive_k128