Update README.md
Browse files
README.md
CHANGED
|
@@ -4,12 +4,24 @@ license: mit
|
|
| 4 |
base_model: camembert-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
- f1
|
| 10 |
model-index:
|
| 11 |
- name: camembert-bank-post-classifier
|
| 12 |
results: []
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,6 +30,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
# camembert-bank-post-classifier
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: 0.5783
|
| 23 |
- Accuracy: 0.8682
|
|
@@ -67,4 +87,4 @@ The following hyperparameters were used during training:
|
|
| 67 |
- Transformers 4.56.1
|
| 68 |
- Pytorch 2.8.0+cu126
|
| 69 |
- Datasets 4.0.0
|
| 70 |
-
- Tokenizers 0.22.0
|
|
|
|
| 4 |
base_model: camembert-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
- text-classification
|
| 8 |
+
- french
|
| 9 |
+
- banking
|
| 10 |
+
- camembert
|
| 11 |
+
- classification
|
| 12 |
+
widget:
|
| 13 |
+
- text: "Nous organisons une formation sur la gestion de projet"
|
| 14 |
+
- text: "Lancement de notre nouvelle application mobile"
|
| 15 |
+
- text: "Séminaire sur la responsabilité sociale d'entreprise"
|
| 16 |
metrics:
|
| 17 |
- accuracy
|
| 18 |
- f1
|
| 19 |
model-index:
|
| 20 |
- name: camembert-bank-post-classifier
|
| 21 |
results: []
|
| 22 |
+
language:
|
| 23 |
+
- fr
|
| 24 |
+
pipeline_tag: text-classification
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
# camembert-bank-post-classifier
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
|
| 33 |
+
It classifies posts on an internal social media in 7 categories :
|
| 34 |
+
- Annonce RH & Vie de l'Entreprise
|
| 35 |
+
- Communication de la Direction & Stratégie
|
| 36 |
+
- Formation & Développement
|
| 37 |
+
- Information & Alerte Pratique
|
| 38 |
+
- Projet, Produit & Innovation
|
| 39 |
+
- RSE & Engagement Citoyen
|
| 40 |
+
- Événement Externe & Partenariat
|
| 41 |
It achieves the following results on the evaluation set:
|
| 42 |
- Loss: 0.5783
|
| 43 |
- Accuracy: 0.8682
|
|
|
|
| 87 |
- Transformers 4.56.1
|
| 88 |
- Pytorch 2.8.0+cu126
|
| 89 |
- Datasets 4.0.0
|
| 90 |
+
- Tokenizers 0.22.0
|