PyLate model based on Speedsy/turkish-multilingual-e5-small-32768

This is a PyLate model finetuned from Speedsy/turkish-multilingual-e5-small-32768 on the train 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: Speedsy/turkish-multilingual-e5-small-32768
Document Length: 180 tokens
Query Length: 32 tokens
Output Dimensionality: 128 tokens
Similarity Function: MaxSim
Training Dataset:
- train
Language: en

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': 179, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Dense({'in_features': 384, 'out_features': 128, '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=pylate_model_id,
)

# 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=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: ['NanoDBPedia', 'NanoFiQA2018', 'NanoHotpotQA', 'NanoMSMARCO', 'NanoNQ', 'NanoSCIDOCS']
Evaluated with pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator

Metric	NanoDBPedia	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNQ	NanoSCIDOCS
MaxSim_accuracy@1	0.78	0.3	0.82	0.38	0.46	0.36
MaxSim_accuracy@3	0.9	0.48	0.9	0.56	0.66	0.5
MaxSim_accuracy@5	0.92	0.54	0.98	0.66	0.7	0.62
MaxSim_accuracy@10	0.96	0.64	0.98	0.76	0.82	0.72
MaxSim_precision@1	0.78	0.3	0.82	0.38	0.46	0.36
MaxSim_precision@3	0.6267	0.2067	0.4733	0.1867	0.2333	0.2333
MaxSim_precision@5	0.612	0.164	0.324	0.132	0.148	0.208
MaxSim_precision@10	0.51	0.106	0.17	0.076	0.086	0.132
MaxSim_recall@1	0.0989	0.1562	0.41	0.38	0.44	0.0757
MaxSim_recall@3	0.1727	0.2975	0.71	0.56	0.64	0.1437
MaxSim_recall@5	0.2452	0.3566	0.81	0.66	0.68	0.2127
MaxSim_recall@10	0.3557	0.457	0.85	0.76	0.77	0.2697
MaxSim_ndcg@10	0.6387	0.3644	0.7904	0.5583	0.6175	0.27
MaxSim_mrr@10	0.8427	0.4125	0.8737	0.4947	0.5782	0.4619
MaxSim_map@100	0.4894	0.3	0.7217	0.5038	0.5679	0.204

Pylate Custom Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with pylate_nano_beir_evaluator.PylateCustomNanoBEIREvaluator

Metric	Value
MaxSim_accuracy@1	0.5167
MaxSim_accuracy@3	0.6667
MaxSim_accuracy@5	0.7367
MaxSim_accuracy@10	0.8133
MaxSim_precision@1	0.5167
MaxSim_precision@3	0.3267
MaxSim_precision@5	0.2647
MaxSim_precision@10	0.18
MaxSim_recall@1	0.2601
MaxSim_recall@3	0.4206
MaxSim_recall@5	0.4941
MaxSim_recall@10	0.577
MaxSim_ndcg@10	0.5399
MaxSim_mrr@10	0.6106
MaxSim_map@100	0.4645

Training Details

Training Dataset

train

Dataset: train at b9b0f7f
Size: 798,036 training samples
Columns: query_id, document_ids, and scores
Approximate statistics based on the first 1000 samples:
query_id document_ids scores
type string list list
details
min: 4 tokens
mean: 5.82 tokens
max: 6 tokens

size: 32 elements

size: 32 elements

	query_id	document_ids	scores
type	string	list	list
details	min: 4 tokens mean: 5.82 tokens max: 6 tokens	size: 32 elements	size: 32 elements

Samples:

query_id	document_ids	scores
`817836`	`['2716076', '6741935', '2681109', '5562684', '3507339', ...]`	`[1.0, 0.7059561610221863, 0.21702419221401215, 0.38270196318626404, 0.20812414586544037, ...]`
`1045170`	`['5088671', '2953295', '8783471', '4268439', '6339935', ...]`	`[1.0, 0.6493034362792969, 0.0692221149802208, 0.17963139712810516, 0.6697239875793457, ...]`
`1154488`	`['6498614', '3770829', '1060712', '2590533', '7672044', ...]`	`[0.9497447609901428, 0.6662212610244751, 0.7423420548439026, 1.0, 0.6580896973609924, ...]`

Loss: pylate.losses.distillation.Distillation

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
learning_rate: 3e-05
num_train_epochs: 1
bf16: 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: 16
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: 1
max_steps: -1
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: 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: 0
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}
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

Training Logs

Epoch	Step	Training Loss	NanoDBPedia_MaxSim_ndcg@10	NanoFiQA2018_MaxSim_ndcg@10	NanoHotpotQA_MaxSim_ndcg@10	NanoMSMARCO_MaxSim_ndcg@10	NanoNQ_MaxSim_ndcg@10	NanoSCIDOCS_MaxSim_ndcg@10	NanoBEIR_mean_MaxSim_ndcg@10
0.0004	20	0.0321	-	-	-	-	-	-	-
0.0008	40	0.0316	-	-	-	-	-	-	-
0.0012	60	0.0305	-	-	-	-	-	-	-
0.0016	80	0.0298	-	-	-	-	-	-	-
0.0020	100	0.0291	-	-	-	-	-	-	-
0.0024	120	0.0286	-	-	-	-	-	-	-
0.0028	140	0.0268	-	-	-	-	-	-	-
0.0032	160	0.0262	-	-	-	-	-	-	-
0.0036	180	0.0282	-	-	-	-	-	-	-
0.0040	200	0.0264	-	-	-	-	-	-	-
0.0044	220	0.0257	-	-	-	-	-	-	-
0.0048	240	0.0267	-	-	-	-	-	-	-
0.0052	260	0.026	-	-	-	-	-	-	-
0.0056	280	0.0258	-	-	-	-	-	-	-
0.0060	300	0.025	-	-	-	-	-	-	-
0.0064	320	0.0238	-	-	-	-	-	-	-
0.0068	340	0.0242	-	-	-	-	-	-	-
0.0072	360	0.0256	-	-	-	-	-	-	-
0.0076	380	0.0259	-	-	-	-	-	-	-
0.0080	400	0.0254	-	-	-	-	-	-	-
0.0084	420	0.0245	-	-	-	-	-	-	-
0.0088	440	0.0253	-	-	-	-	-	-	-
0.0092	460	0.0252	-	-	-	-	-	-	-
0.0096	480	0.0238	-	-	-	-	-	-	-
0.0100	500	0.0259	0.6349	0.3320	0.7611	0.5174	0.6534	0.2696	0.5281
0.0104	520	0.0241	-	-	-	-	-	-	-
0.0108	540	0.024	-	-	-	-	-	-	-
0.0112	560	0.0247	-	-	-	-	-	-	-
0.0116	580	0.0234	-	-	-	-	-	-	-
0.0120	600	0.0244	-	-	-	-	-	-	-
0.0124	620	0.0261	-	-	-	-	-	-	-
0.0128	640	0.0267	-	-	-	-	-	-	-
0.0132	660	0.0246	-	-	-	-	-	-	-
0.0136	680	0.0243	-	-	-	-	-	-	-
0.0140	700	0.0231	-	-	-	-	-	-	-
0.0144	720	0.0247	-	-	-	-	-	-	-
0.0148	740	0.0228	-	-	-	-	-	-	-
0.0152	760	0.0239	-	-	-	-	-	-	-
0.0156	780	0.0255	-	-	-	-	-	-	-
0.0160	800	0.0238	-	-	-	-	-	-	-
0.0164	820	0.0249	-	-	-	-	-	-	-
0.0168	840	0.0249	-	-	-	-	-	-	-
0.0172	860	0.0239	-	-	-	-	-	-	-
0.0176	880	0.0247	-	-	-	-	-	-	-
0.0180	900	0.0257	-	-	-	-	-	-	-
0.0184	920	0.0248	-	-	-	-	-	-	-
0.0188	940	0.0235	-	-	-	-	-	-	-
0.0192	960	0.0232	-	-	-	-	-	-	-
0.0196	980	0.0229	-	-	-	-	-	-	-
0.0200	1000	0.024	0.6362	0.3393	0.7805	0.5170	0.6149	0.2639	0.5253
0.0204	1020	0.0233	-	-	-	-	-	-	-
0.0209	1040	0.0227	-	-	-	-	-	-	-
0.0213	1060	0.0237	-	-	-	-	-	-	-
0.0217	1080	0.0244	-	-	-	-	-	-	-
0.0221	1100	0.0225	-	-	-	-	-	-	-
0.0225	1120	0.023	-	-	-	-	-	-	-
0.0229	1140	0.0241	-	-	-	-	-	-	-
0.0233	1160	0.0248	-	-	-	-	-	-	-
0.0237	1180	0.0246	-	-	-	-	-	-	-
0.0241	1200	0.0256	-	-	-	-	-	-	-
0.0245	1220	0.0235	-	-	-	-	-	-	-
0.0249	1240	0.0221	-	-	-	-	-	-	-
0.0253	1260	0.024	-	-	-	-	-	-	-
0.0257	1280	0.0233	-	-	-	-	-	-	-
0.0261	1300	0.0233	-	-	-	-	-	-	-
0.0265	1320	0.0236	-	-	-	-	-	-	-
0.0269	1340	0.0231	-	-	-	-	-	-	-
0.0273	1360	0.0244	-	-	-	-	-	-	-
0.0277	1380	0.0225	-	-	-	-	-	-	-
0.0281	1400	0.0223	-	-	-	-	-	-	-
0.0285	1420	0.0245	-	-	-	-	-	-	-
0.0289	1440	0.0235	-	-	-	-	-	-	-
0.0293	1460	0.0244	-	-	-	-	-	-	-
0.0297	1480	0.0234	-	-	-	-	-	-	-
0.0301	1500	0.0238	0.6391	0.3643	0.7656	0.5385	0.6161	0.2763	0.5333
0.0305	1520	0.0234	-	-	-	-	-	-	-
0.0309	1540	0.0218	-	-	-	-	-	-	-
0.0313	1560	0.0226	-	-	-	-	-	-	-
0.0317	1580	0.0229	-	-	-	-	-	-	-
0.0321	1600	0.0234	-	-	-	-	-	-	-
0.0325	1620	0.0243	-	-	-	-	-	-	-
0.0329	1640	0.0234	-	-	-	-	-	-	-
0.0333	1660	0.0225	-	-	-	-	-	-	-
0.0337	1680	0.022	-	-	-	-	-	-	-
0.0341	1700	0.022	-	-	-	-	-	-	-
0.0345	1720	0.0225	-	-	-	-	-	-	-
0.0349	1740	0.023	-	-	-	-	-	-	-
0.0353	1760	0.0234	-	-	-	-	-	-	-
0.0357	1780	0.0242	-	-	-	-	-	-	-
0.0361	1800	0.0227	-	-	-	-	-	-	-
0.0365	1820	0.0228	-	-	-	-	-	-	-
0.0369	1840	0.0218	-	-	-	-	-	-	-
0.0373	1860	0.0236	-	-	-	-	-	-	-
0.0377	1880	0.0242	-	-	-	-	-	-	-
0.0381	1900	0.0234	-	-	-	-	-	-	-
0.0385	1920	0.0236	-	-	-	-	-	-	-
0.0389	1940	0.023	-	-	-	-	-	-	-
0.0393	1960	0.0228	-	-	-	-	-	-	-
0.0397	1980	0.0245	-	-	-	-	-	-	-
0.0401	2000	0.0228	0.6387	0.3644	0.7904	0.5583	0.6175	0.2700	0.5399

Framework Versions

Python: 3.11.12
Sentence Transformers: 3.4.1
PyLate: 1.1.7
Transformers: 4.48.2
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 3.6.0
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}
}

Speedsy
/

turkish-multilingual-e5-small-32768-colbert-2000