You can deploy this model and start earning money today!

Views

No views yet

SPLADE Sparse Encoder

Name: SPLADE_camembert-base_STS
Availability: InStock

This is a SPLADE Sparse Encoder model finetuned from almanach/camembert-base on the french_sts dataset using the sentence-transformers library. It maps sentences & paragraphs to a 32005-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

Model Type: SPLADE Sparse Encoder
Base model: almanach/camembert-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 32005 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- french_sts
Language: fr

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Sparse Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sparse Encoders on Hugging Face

Full Model Architecture

SparseEncoder(
  (0): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'CamembertForMaskedLM'})
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 32005})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

python

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("CATIE-AQ/SPLADE_camembert-base_STS")
# Run inference
sentences = [
    "Oui, je peux vous dire d'après mon expérience personnelle qu'ils ont certainement sifflé.",
    "Il est vrai que les bombes de la Seconde Guerre mondiale faisaient un bruit de sifflet lorsqu'elles tombaient.",
    "J'envisage de dépenser les 48 dollars par mois pour le système GTD (Getting things done) annoncé par David Allen.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 32005]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.1034, 0.1443],
#         [0.1034, 1.0000, 0.0588],
#         [0.1443, 0.0588, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Datasets: sts-dev and sts-test
Evaluated with SparseEmbeddingSimilarityEvaluator

Metric	sts-dev	sts-test
pearson_cosine	0.7166	0.7246
spearman_cosine	0.7147	0.6623
active_dims	28.9952	56.8902
sparsity_ratio	0.9991	0.9982

Training Details

Training Dataset

french_sts

Dataset: french_sts at 47128cc
Size: 12,227 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 11.68 tokens
max: 30 tokens
min: 6 tokens
mean: 11.7 tokens
max: 35 tokens
min: 0.0
mean: 0.44
max: 1.0

Samples:

sentence1	sentence2	score
`Un avion est en train de décoller.`	`Un avion est en train de décoller.`	`1.0`
`Un homme est en train de fumer.`	`Un homme fait du patinage.`	`0.10000000149011612`
`Une personne jette un chat au plafond.`	`Une personne jette un chat au plafond.`	`1.0`

Loss: SpladeLoss with these parameters:
json
1{ 2 "loss": "SparseCosineSimilarityLoss(loss_fct='torch.nn.modules.loss.MSELoss')", 3 "document_regularizer_weight": 0.003 4}

Evaluation Dataset

french_sts

Dataset: french_sts at 47128cc
Size: 3,526 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 19.04 tokens
max: 52 tokens
min: 6 tokens
mean: 18.97 tokens
max: 56 tokens
min: 0.0
mean: 0.43
max: 1.0

Samples:

sentence1	sentence2	score
`Un homme avec un casque de sécurité est en train de danser.`	`Un homme portant un casque de sécurité est en train de danser.`	`1.0`
`Un jeune enfant monte à cheval.`	`Un enfant monte à cheval.`	`0.949999988079071`
`Un homme donne une souris à un serpent.`	`L'homme donne une souris au serpent.`	`1.0`

Loss: SpladeLoss with these parameters:
json
1{ 2 "loss": "SparseCosineSimilarityLoss(loss_fct='torch.nn.modules.loss.MSELoss')", 3 "document_regularizer_weight": 0.003 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
bf16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 5e-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
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}
tp_size: 0
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
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
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-dev_spearman_cosine	sts-test_spearman_cosine
-1	-1	-	-	0.4596	-
0.1307	100	0.051	-	-	-
0.2614	200	0.034	-	-	-
0.3922	300	0.0337	-	-	-
0.5229	400	0.0318	-	-	-
0.6536	500	0.0324	-	-	-
0.7843	600	0.0317	-	-	-
0.9150	700	0.0318	-	-	-
1.0	765	-	0.0521	0.6820	-
1.0458	800	0.0321	-	-	-
1.1765	900	0.025	-	-	-
1.3072	1000	0.0265	-	-	-
1.4379	1100	0.0231	-	-	-
1.5686	1200	0.0226	-	-	-
1.6993	1300	0.0246	-	-	-
1.8301	1400	0.0227	-	-	-
1.9608	1500	0.0233	-	-	-
2.0	1530	-	0.0420	0.7144	-
2.0915	1600	0.0188	-	-	-
2.2222	1700	0.0166	-	-	-
2.3529	1800	0.0168	-	-	-
2.4837	1900	0.0176	-	-	-
2.6144	2000	0.0168	-	-	-
2.7451	2100	0.0162	-	-	-
2.8758	2200	0.0153	-	-	-
3.0	2295	-	0.0447	0.7147	-
-1	-1	-	-	-	0.6623

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.0.0
Transformers: 4.51.3
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 2.16.0
Tokenizers: 0.21.0

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",
}

SpladeLoss

bibtex

@misc{formal2022distillationhardnegativesampling,
      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
      year={2022},
      eprint={2205.04733},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2205.04733},
}

FlopsLoss

bibtex

@article{paria2020minimizing,
    title={Minimizing flops to learn efficient sparse representations},
    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
    journal={arXiv preprint arXiv:2004.05665},
    year={2020}
}

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 11.68 tokens max: 30 tokens	min: 6 tokens mean: 11.7 tokens max: 35 tokens	min: 0.0 mean: 0.44 max: 1.0