chg: [RELEASE] Bumped release number and updated CHANGELOG.

Author: cedricbonhomme

CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## Release 1.1.0 (2025-02-27)
+
+### News
+
+- Trainers: Support of roberta-base for the text classifier with improved
+  settings for TrainingArguments.
+- Validators: Validator for severity classification.
+
+
 ## Release 1.0.0 (2025-02-25)
 
 ### News

README.md

@@ -109,10 +109,28 @@ Using CUDA (Nvidia GPU).
 
 #### Training for classification
 
+```bash
+$ vulntrain-train-severity-classification --help
+usage: vulntrain-train-severity-classification [-h] [--base-model {distilbert-base-uncased,roberta-base}] [--dataset-id DATASET_ID] --repo-id REPO_ID [--model-save-dir MODEL_SAVE_DIR]
+
+Train a vulnerability classification model with a mapping on the severity.
+
+options:
+  -h, --help            show this help message and exit
+  --base-model {distilbert-base-uncased,roberta-base}
+                        Base model to use.
+  --dataset-id DATASET_ID
+                        Path of the dataset. Local dataset or repository on the HF hub.
+  --repo-id REPO_ID     The name of the repository you want to push your object to. It should contain your organization name when pushing to a given organization.
+  --model-save-dir MODEL_SAVE_DIR
+                        The path to a directory where the tokenizer and the model will be saved.
 
-- distilbert with CVS scores mapping
-- tf-idf on the vulnerability descriptions.
 
+$ vulntrain-train-severity-classification --base-model roberta-base --dataset-id CIRCL/vulnerability-scores --repo-id CIRCL/vulnerability-severity-classification-roberta-base
+...
+...
+...
+```
 
 
 ### Validation

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [project]
 name = "VulnTrain"
-version = "1.0.0"
+version = "1.1.0"
 description = "Generate datasets amd models based on vulnerabilities data from Vulnerability-Lookup."
 authors = [
     {name = "Cédric Bonhomme",email = "[email protected]"}