louisbrulenaudet / lemone-embed-m-boost

huggingface.co
Total runs: 124
24-hour runs: 0
7-day runs: 6
30-day runs: 35
Model's Last Updated: October 03 2024
sentence-similarity

Introduction of lemone-embed-m-boost

Model Details of lemone-embed-m-boost

Lemone-Embed: A Series of Fine-Tuned Embedding Models for French Taxation

This series is made up of 7 models, 3 basic models of different sizes trained on 1 epoch, 3 models trained on 2 epochs making up the Boost series and a Pro model with a non-Roberta architecture.

This sentence transformers model, specifically designed for French taxation, has been fine-tuned on a dataset comprising 43 million tokens, integrating a blend of semi-synthetic and fully synthetic data generated by GPT-4 Turbo and Llama 3.1 70B, which have been further refined through evol-instruction tuning and manual curation.

The model is tailored to meet the specific demands of information retrieval across large-scale tax-related corpora, supporting the implementation of production-ready Retrieval-Augmented Generation (RAG) applications. Its primary purpose is to enhance the efficiency and accuracy of legal processes in the taxation domain, with an emphasis on delivering consistent performance in real-world settings, while also contributing to advancements in legal natural language processing research.

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-base . It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details
Model Description
  • Model Type: Sentence Transformer
  • Base model: intfloat/multilingual-e5-base
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity
  • Developed by: Louis Brulé Naudet
  • Funded by: Microsoft for Startups
  • Shared by: Louis Brulé Naudet
  • Model type: Sentence Transformers
  • Language(s) (NLP): FR
  • License: Apache 2
  • Finetuned from model: intfloat/multilingual-e5-base
Model Sources
Full Model Architecture
SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)
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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("louisbrulenaudet/lemone-embed-m-boost")
# Run inference
sentences = [
    "query: Décrivez avec précision les étapes détaillées requises pour traiter les réclamations collectives résultant de désastres agricoles comme définies dans l'article R*198-2 du Livre des procédures fiscales.",
    "passage: Selon l'article R*198-2 du Livre des procédures fiscales, le traitement des réclamations collectives en cas de catastrophes naturelles impactant les cultures agricoles, incluant des phénomènes tels que la grêle ou les inondations, exige la collaboration de plusieurs entités administratives. Initialement, deux commissaires sont nommés par l'administration fiscale pour superviser le processus. Ils sont assistés par un délégué de l'administration des impôts. Avant toute action, le maire de la commune affectée est notifié au moins dix jours avant l'inspection prévue, et il est chargé de communiquer cette date aux résidents via des affichages publics. Les agriculteurs affectés doivent alors rapporter leurs pertes à la mairie avant la réalisation d'un constat officiel par l'inspecteur des impôts, qui sera consigné dans un procès-verbal. Une fois ce document clôturé, aucune réclamation supplémentaire n'est acceptée.",
    "passage: Selon les dispositions de l'article R*196-6 du Livre des procédures fiscales, il est attribué aux sujets fiscaux un intervalle précisément défini pour élever des réclamations à l'égard des taxes, cotisations et autres prélèvements relatifs aux céréales et leurs transformés. Ce délai se prolonge jusqu'à la fin de la campagne agricole suivante celle au cours de laquelle l'avis de mise en recouvrement de la taxe a été notifié ou le règlement de l'imposition contestée effectué, permettant ainsi aux parties prenantes de se prévaloir de leurs prérogatives contestataires avec une certitude temporelle.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Evaluation
Metrics
Information Retrieval
Metric Value
cosine_accuracy@1 0.9743
cosine_accuracy@3 0.991
cosine_accuracy@5 0.9936
cosine_accuracy@10 0.9955
cosine_precision@1 0.9743
cosine_precision@3 0.3303
cosine_precision@5 0.1987
cosine_precision@10 0.0996
cosine_recall@1 0.9743
cosine_recall@3 0.991
cosine_recall@5 0.9936
cosine_recall@10 0.9955
cosine_ndcg@10 0.9862
cosine_mrr@10 0.9831
cosine_map@100 0.9833
dot_accuracy@1 0.9743
dot_accuracy@3 0.991
dot_accuracy@5 0.9936
dot_accuracy@10 0.9955
dot_precision@1 0.9743
dot_precision@3 0.3303
dot_precision@5 0.1987
dot_precision@10 0.0996
dot_recall@1 0.9743
dot_recall@3 0.991
dot_recall@5 0.9936
dot_recall@10 0.9955
dot_ndcg@10 0.9862
dot_mrr@10 0.9831
dot_map@100 0.9833
Training Details
Training Dataset
  • Size: 296,234 training samples
  • Columns: query , positive , and negative
  • Approximate statistics based on the first 1000 samples:
    query positive negative
    type string string string
    details
    • min: 24 tokens
    • mean: 54.2 tokens
    • max: 179 tokens
    • min: 75 tokens
    • mean: 182.28 tokens
    • max: 332 tokens
    • min: 53 tokens
    • mean: 190.2 tokens
    • max: 456 tokens
  • Loss: CachedGISTEmbedLoss with these parameters:
    {'guide': SentenceTransformer(
      (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
      (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
      (2): Normalize()
    ), 'temperature': 0.01}
    
Training Hyperparameters
Non-Default Hyperparameters
  • eval_strategy : steps
  • per_device_train_batch_size : 512
  • learning_rate : 2e-05
  • num_train_epochs : 2
  • warmup_ratio : 0.1
  • fp16 : True
  • batch_sampler : no_duplicates
All Hyperparameters
Click to expand
  • overwrite_output_dir : False
  • do_predict : False
  • eval_strategy : steps
  • prediction_loss_only : True
  • per_device_train_batch_size : 512
  • 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 : 2e-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 : 2
  • 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 : 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 : 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 : False
  • hub_always_push : False
  • gradient_checkpointing : False
  • gradient_checkpointing_kwargs : None
  • include_inputs_for_metrics : False
  • 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
  • eval_use_gather_object : False
  • batch_sampler : no_duplicates
  • multi_dataset_batch_sampler : proportional
Environmental Impact

Carbon emissions were measured using CodeCarbon .

  • Energy Consumed : 2.535 kWh
  • Carbon Emitted : 0.936 kg of CO2
  • Hours Used : 4.578 hours
Training Hardware
  • On Cloud : No
  • GPU Model : 1 x NVIDIA H100 NVL
  • CPU Model : AMD EPYC 9V84 96-Core Processor
  • RAM Size : 314.69 GB
Framework Versions
  • Python: 3.10.12
  • Sentence Transformers: 3.1.1
  • Transformers: 4.44.2
  • PyTorch: 2.3.0+cu121
  • Accelerate: 0.33.0
  • Datasets: 2.21.0
  • Tokenizers: 0.19.1
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",
}

If you use this code in your research, please use the following BibTeX entry.

@misc{louisbrulenaudet2024,
  author =       {Louis Brulé Naudet},
  title =        {Lemone-Embed: A Series of Fine-Tuned Embedding Models for French Taxation},
  year =         {2024}
  howpublished = {\url{https://huggingface.co/datasets/louisbrulenaudet/lemone-embed-m-boost}},
}
Feedback

If you have any feedback, please reach out at [email protected] .

Runs of louisbrulenaudet lemone-embed-m-boost on huggingface.co

124
Total runs
0
24-hour runs
2
3-day runs
6
7-day runs
35
30-day runs

More Information About lemone-embed-m-boost huggingface.co Model

More lemone-embed-m-boost license Visit here:

https://choosealicense.com/licenses/apache-2.0

lemone-embed-m-boost huggingface.co

lemone-embed-m-boost huggingface.co is an AI model on huggingface.co that provides lemone-embed-m-boost's model effect (), which can be used instantly with this louisbrulenaudet lemone-embed-m-boost model. huggingface.co supports a free trial of the lemone-embed-m-boost model, and also provides paid use of the lemone-embed-m-boost. Support call lemone-embed-m-boost model through api, including Node.js, Python, http.

louisbrulenaudet lemone-embed-m-boost online free

lemone-embed-m-boost huggingface.co is an online trial and call api platform, which integrates lemone-embed-m-boost's modeling effects, including api services, and provides a free online trial of lemone-embed-m-boost, you can try lemone-embed-m-boost online for free by clicking the link below.

louisbrulenaudet lemone-embed-m-boost online free url in huggingface.co:

https://huggingface.co/louisbrulenaudet/lemone-embed-m-boost

lemone-embed-m-boost install

lemone-embed-m-boost is an open source model from GitHub that offers a free installation service, and any user can find lemone-embed-m-boost on GitHub to install. At the same time, huggingface.co provides the effect of lemone-embed-m-boost install, users can directly use lemone-embed-m-boost installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

lemone-embed-m-boost install url in huggingface.co:

https://huggingface.co/louisbrulenaudet/lemone-embed-m-boost

Url of lemone-embed-m-boost

Provider of lemone-embed-m-boost huggingface.co

louisbrulenaudet
ORGANIZATIONS

Other API from louisbrulenaudet