verbatims-valid

apprentissage-sirius/verbatims-valid

verbatims-valid is a text classification model from apprentissage-sirius. Use it when you need a label for a piece of text. It is set up for sklearn. The card lists the license as mit.

This is a Support Vector Classifier model trained on SIRIUS dataset.As input, the model takes text embeddings encoded with camembert-base (768 tokens)

Downloads · 30 days

Access

Public

Updated Mar 13, 2025

Repo size

6.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pkl6.8 MB · 99%

At a glance

Task: Text Classification
Library: sklearn
License: mit
Access: Public
Created: Mar 13, 2025
Updated: Mar 13, 2025
SHA: 789a3687

Try a prompt

Model card

From the Hugging Face model README

Model description

This is a Support Vector Classifier model trained on SIRIUS dataset.As input, the model takes text embeddings encoded with camembert-base (768 tokens)

Intended uses & limitations

This model is not ready to be used in production.

Training Procedure

[More Information Needed]

Hyperparameters

<details> <summary> Click to expand </summary>

Hyperparameter	Value
memory
steps	[('columntransformer', ColumnTransformer(transformers=[('num',<br /> Pipeline(steps=[('imputer',<br /> SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()),<br /> ('pca',<br /> PCA(n_components=292))]),<br /> Index(['emb_1', 'emb_2', 'emb_3', 'emb_4', 'emb_5', 'emb_6', 'emb_7', 'emb_8',<br /> 'emb_9', 'emb_10',<br /> ...<br /> 'emb_759', 'emb_760', 'emb_761', 'emb_762', 'emb_763', 'emb_764',<br /> 'emb_765', 'emb_766', 'emb_767', 'emb_768'],<br /> dtype='object', length=768))],<br /> verbose_feature_names_out=False)), ('svc', SVC(probability=True, random_state=42))]
verbose	False
columntransformer	ColumnTransformer(transformers=[('num',<br /> Pipeline(steps=[('imputer',<br /> SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()),<br /> ('pca',<br /> PCA(n_components=292))]),<br /> Index(['emb_1', 'emb_2', 'emb_3', 'emb_4', 'emb_5', 'emb_6', 'emb_7', 'emb_8',<br /> 'emb_9', 'emb_10',<br /> ...<br /> 'emb_759', 'emb_760', 'emb_761', 'emb_762', 'emb_763', 'emb_764',<br /> 'emb_765', 'emb_766', 'emb_767', 'emb_768'],<br /> dtype='object', length=768))],<br /> verbose_feature_names_out=False)
svc	SVC(probability=True, random_state=42)
columntransformer__force_int_remainder_cols	True
columntransformer__n_jobs
columntransformer__remainder	drop
columntransformer__sparse_threshold	0.3
columntransformer__transformer_weights
columntransformer__transformers	[('num', Pipeline(steps=[('imputer', SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()), ('pca', PCA(n_components=292))]), Index(['emb_1', 'emb_2', 'emb_3', 'emb_4', 'emb_5', 'emb_6', 'emb_7', 'emb_8',<br /> 'emb_9', 'emb_10',<br /> ...<br /> 'emb_759', 'emb_760', 'emb_761', 'emb_762', 'emb_763', 'emb_764',<br /> 'emb_765', 'emb_766', 'emb_767', 'emb_768'],<br /> dtype='object', length=768))]
columntransformer__verbose	False
columntransformer__verbose_feature_names_out	False
columntransformer__num	Pipeline(steps=[('imputer', SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()), ('pca', PCA(n_components=292))])
columntransformer__num__memory
columntransformer__num__steps	[('imputer', SimpleImputer(strategy='median')), ('scaler', StandardScaler()), ('pca', PCA(n_components=292))]
columntransformer__num__verbose	False
columntransformer__num__imputer	SimpleImputer(strategy='median')
columntransformer__num__scaler	StandardScaler()
columntransformer__num__pca	PCA(n_components=292)
columntransformer__num__imputer__add_indicator	False
columntransformer__num__imputer__copy	True
columntransformer__num__imputer__fill_value
columntransformer__num__imputer__keep_empty_features	False
columntransformer__num__imputer__missing_values	nan
columntransformer__num__imputer__strategy	median
columntransformer__num__scaler__copy	True
columntransformer__num__scaler__with_mean	True
columntransformer__num__scaler__with_std	True
columntransformer__num__pca__copy	True
columntransformer__num__pca__iterated_power	auto
columntransformer__num__pca__n_components	292
columntransformer__num__pca__n_oversamples	10
columntransformer__num__pca__power_iteration_normalizer	auto
columntransformer__num__pca__random_state
columntransformer__num__pca__svd_solver	auto
columntransformer__num__pca__tol	0.0
columntransformer__num__pca__whiten	False
svc__C	1.0
svc__break_ties	False
svc__cache_size	200
svc__class_weight
svc__coef0	0.0
svc__decision_function_shape	ovr
svc__degree	3
svc__gamma	scale
svc__kernel	rbf
svc__max_iter	-1
svc__probability	True
svc__random_state	42
svc__shrinking	True
svc__tol	0.001
svc__verbose	False

</details>

Model Plot

Evaluation Results

Metric	Value
accuracy	0.928063
f1 score	0.922716

Confusion Matrix

How to Get Started with the Model

[More Information Needed]

Model Card Authors

huynhdoo

Model Card Contact

You can contact the model card authors through following channels: [More Information Needed]

Citation

BibTeX

@inproceedings{...,year={2024}}

get_started_code

import pickle as pickle with open(pkl_filename, 'rb') as file: pipe = pickle.load(file)

Task: Text Classification
Library: sklearn
License: mit
Created: Mar 13, 2025
Updated: Mar 13, 2025