Update README.md

README.md

@@ -1,62 +1,217 @@
 ---
+language: fr
+datasets:
+- etalab-ia/piaf
+- fquad
+- lincoln/newsquadfr
+- pragnakalp/squad_v2_french_translated
+- CATIE-AQ/frenchQA
 library_name: transformers
 license: mit
 base_model: almanach/moderncamembert-cv2-base
-tags:
-- generated_from_trainer
-datasets:
-- french_qa
-model-index:
-- name: moderncamembert-cv2-base-QA
-  results: []
+metrics:
+- f1
+- exact_match
+widget:
+- text: Combien de personnes utilisent le français tous les jours ?
+  context: >-
+    Le français est une langue indo-européenne de la famille des langues romanes
+    dont les locuteurs sont appelés francophones. Elle est parfois surnommée la
+    langue de Molière.  Le français est parlé, en 2023, sur tous les continents
+    par environ 321 millions de personnes : 235 millions l'emploient
+    quotidiennement et 90 millions en sont des locuteurs natifs. En 2018, 80
+    millions d'élèves et étudiants s'instruisent en français dans le monde.
+    Selon l'Organisation internationale de la francophonie (OIF), il pourrait y
+    avoir 700 millions de francophones sur Terre en 2050.
+co2_eq_emissions: 46
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# moderncamembert-cv2-base-QA
-
-This model is a fine-tuned version of [almanach/moderncamembert-cv2-base](https://huggingface.co/almanach/moderncamembert-cv2-base) on the french_qa dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.0697
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.4741        | 1.0   | 27790 | 0.6610          |
-| 0.2795        | 2.0   | 55580 | 0.7165          |
-| 0.1419        | 3.0   | 83370 | 1.0697          |
-
-
-### Framework versions
 
-- Transformers 4.51.3
-- Pytorch 2.6.0+cu124
-- Datasets 2.16.0
-- Tokenizers 0.21.0
+# ModernQAmembert
+
+## Model Description
+We present **ModernQAmembert**, which is a [Moderncamembert-cv2-base](https://huggingface.co/almanach/moderncamembert-cv2-base) fine-tuned for the Question-Answering task for the French language on four French Q&A datasets composed of contexts and questions with their answers inside the context (= SQuAD 1.0 format) but also contexts and questions with their answers not inside the context (= SQuAD 2.0 format).
+All these datasets were concatenated into a single dataset that we called [frenchQA](https://huggingface.co/datasets/CATIE-AQ/frenchQA).
+This represents a total of over **221,348 context/question/answer triplets used to finetune this model and 6,376 to test it**.  
+Our methodology is described in a blog post available in [English](https://blog.vaniila.ai/en/QA_en/) or [French](https://blog.vaniila.ai/QA/).
+
+
+## Results (french QA test split)
+| Model | Parameters | Context       | Exact_match | F1  | Answer_F1 | NoAnswer_F1 |
+| ----------- | ----------- | ----------- | ----------- | ----------- |----------- |----------- |
+| [etalab/camembert-base-squadFR-fquad-piaf](https://huggingface.co/AgentPublic/camembert-base-squadFR-fquad-piaf) | 110M | 512 tokens  |  39.30       | 51.55       | 79.54 | 23.58
+| [QAmembert](https://huggingface.co/CATIE-AQ/QAmembert)|  110M | 512 tokens   |  77.14       | 86.88       | 75.66 | 98.11
+| [QAmembert2](https://huggingface.co/CATIE-AQ/QAmembert2)| 112M | 1024 tokens   | 76.47       | 88.25       | 78.66 |   97.84
+| [QAmemberta](https://huggingface.co/CATIE-AQ/QAmemberta) | 111M | 1024 tokens   |  **78.18**       | **89.53**       | **81.40** | 97.64
+| ModernQAmembert (this version) | 136M | 8 192 tokens   |  76.73       | 88.85       |  79.45 | 98.24
+| [QAmembert-large](https://huggingface.co/CATIE-AQ/QAmembert-large)| 336M |  512 tokens   | 77.14       | 88.74       | 78.83 | **98.65**
+
+
+Looking at the “Answer_f1” column, Etalab's model appears to be competitive on texts where the answer to the question is indeed in the text provided (it does better than QAmemBERT-large, for example). However, the fact that it doesn't handle texts where the answer to the question is not in the text provided is a drawback.  
+In all cases, whether in terms of metrics, number of parameters or context size, QAmemBERTa achieves the best results.  
+We therefore invite the reader to choose this model.
+
+### Usage
+
+```python
+from transformers import pipeline
+
+qa = pipeline('question-answering', model='CATIE-AQ/ModernQAmembert', tokenizer='CATIE-AQ/ModernQAmembert')
+
+result = qa({
+    'question': "Combien de personnes utilisent le français tous les jours ?",
+    'context': "Le français est une langue indo-européenne de la famille des langues romanes dont les locuteurs sont appelés francophones. Elle est parfois surnommée la langue de Molière.  Le français est parlé, en 2023, sur tous les continents par environ 321 millions de personnes : 235 millions l'emploient quotidiennement et 90 millions en sont des locuteurs natifs. En 2018, 80 millions d'élèves et étudiants s'instruisent en français dans le monde. Selon l'Organisation internationale de la francophonie (OIF), il pourrait y avoir 700 millions de francophones sur Terre en 2050."
+})
+
+if result['score'] < 0.01:
+    print("La réponse n'est pas dans le contexte fourni.")
+else :
+    print(result['answer'])
+```
+
+
+## Environmental Impact
+
+*Carbon emissions were estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.*  
+- **Hardware Type:** A100 PCIe 40/80GB
+- **Hours used:** 5h and 38 min
+- **Cloud Provider:** Private Infrastructure
+- **Carbon Efficiency (kg/kWh):** 0.032kg (estimated from [electricitymaps](https://app.electricitymaps.com/zone/FR) ; we take the carbon intensity in France for November 20, 2024.)
+- **Carbon Emitted** *(Power consumption x Time x Carbon produced based on location of power grid)*: **0.046 kg eq. CO2**
+
+
+
+## Citations
+
+
+### ModernQAmembert
+```
+@misc {NERmemberta2024,
+    author       = { {BOURDOIS, Loïck} },  
+    organization = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+	title        = { ModernQAmembert},
+	year         = 2025,
+	url          = { https://huggingface.co/CATIE-AQ/ModernQAmembert },
+	doi          = { 10.57967/hf/3640 },
+	publisher    = { Hugging Face }
+}
+```
+
+### Moderncamembert-cv2-base
+```
+@misc{antoun2025modernbertdebertav3examiningarchitecture,
+      title={ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance}, 
+      author={Wissam Antoun and Benoît Sagot and Djamé Seddah},
+      year={2025},
+      eprint={2504.08716},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2504.08716}, 
+}
+```
+
+### QAmemBERT2 & QAmemBERTa
+```
+@misc {qamemberta2024,
+    author       = { {BOURDOIS, Loïck} },  
+    organization  = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+	title        = { QAmemberta (Revision 976a70b) },
+	year         = 2024,
+	url          = { https://huggingface.co/CATIE-AQ/QAmemberta },
+	doi          = { 10.57967/hf/3639 },
+	publisher    = { Hugging Face }
+}
+```
+
+### CamemBERT 2.0
+```
+@misc{antoun2024camembert20smarterfrench,
+      title={CamemBERT 2.0: A Smarter French Language Model Aged to Perfection}, 
+      author={Wissam Antoun and Francis Kulumba and Rian Touchent and Éric de la Clergerie and Benoît Sagot and Djamé Seddah},
+      year={2024},
+      eprint={2411.08868},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2411.08868}, 
+}
+```
+
+### QAmemBERT
+```
+@misc {qamembert2023,  
+    author       = { {ALBAR, Boris and BEDU, Pierre and BOURDOIS, Loïck} },  
+    organization  = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+    title        = { QAmembert (Revision 9685bc3) },  
+    year         = 2023,  
+    url          = { https://huggingface.co/CATIE-AQ/QAmembert},  
+    doi          = { 10.57967/hf/0821 },  
+    publisher    = { Hugging Face }  
+}
+```
+
+### CamemBERT
+```
+@inproceedings{martin2020camembert,
+  title={CamemBERT: a Tasty French Language Model},
+  author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t},
+  booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
+  year={2020}
+}
+```
+
+### frenchQA
+```
+@misc {frenchQA2023,  
+    author       = { {ALBAR, Boris and BEDU, Pierre and BOURDOIS, Loïck} },  
+    organization  = { {Centre Aquitain des Technologies de l'Information et Electroniques} },  
+    title        = { frenchQA (Revision 6249cd5) },  
+    year         = 2023,  
+    url          = { https://huggingface.co/CATIE-AQ/frenchQA },  
+    doi          = { 10.57967/hf/0862 },  
+    publisher    = { Hugging Face }  
+}
+```
+
+### PIAF
+```
+@inproceedings{KeraronLBAMSSS20,
+  author    = {Rachel Keraron and
+               Guillaume Lancrenon and
+               Mathilde Bras and
+               Fr{\'{e}}d{\'{e}}ric Allary and
+               Gilles Moyse and
+               Thomas Scialom and
+               Edmundo{-}Pavel Soriano{-}Morales and
+               Jacopo Staiano},
+  title     = {Project {PIAF:} Building a Native French Question-Answering Dataset},
+  booktitle = {{LREC}},
+  pages     = {5481--5490},
+  publisher = {European Language Resources Association},
+  year      = {2020}
+}
+```
+
+### FQuAD
+```
+@article{dHoffschmidt2020FQuADFQ,
+  title={FQuAD: French Question Answering Dataset},
+  author={Martin d'Hoffschmidt and Maxime Vidal and Wacim Belblidia and Tom Brendl'e and Quentin Heinrich},
+  journal={ArXiv},
+  year={2020},
+  volume={abs/2002.06071}
+}
+```
+
+### lincoln/newsquadfr
+```
+Hugging Face repository: https://hf.co/datasets/lincoln/newsquadfr
+```
+
+### pragnakalp/squad_v2_french_translated
+```
+Hugging Face repository: https://hf.co/datasets/pragnakalp/squad_v2_french_translated
+```
+
+
+## License
+MIT