Monsia commited on
Commit
1272633
1 Parent(s): 85140d2

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - fr
4
+ tags:
5
+ - classification
6
+ license: apache-2.0
7
+ metrics:
8
+ - accuracy
9
+ widget:
10
+ - text: "tchai on est morts. on va se faire vacciner et ils vont contrôler comme les marionnettes avec des fils. d'après les 'ont dit'..."
11
+ ---
12
+ # camembert-fr-covid-tweet-sentiment-classification
13
+ This model is a fine-tune checkpoint of [Yanzhu/bertweetfr-base](https://huggingface.co/Yanzhu/bertweetfr-base), fine-tuned on SST-2.
14
+ This model reaches an accuracy of 71% on the dev set.
15
+ In this dataset, given a tweet, the goal was to infer the underlying topic of the tweet by choosing from four topics classes:
16
+ -positif
17
+ -negatif
18
+ -neutre
19
+
20
+ # Pipelining the Model
21
+
22
+ ```python
23
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
24
+ tokenizer = AutoTokenizer.from_pretrained("Monsia/camembert-fr-covid-tweet-sentiment-classification")
25
+ model = AutoModelForSequenceClassification.from_pretrained("Monsia/camembert-fr-covid-tweet-sentiment-classification")
26
+ nlp_topic_classif = transformers.pipeline('topics-classification', model = model, tokenizer = tokenizer)
27
+ nlp_topic_classif("tchai on est morts. on va se faire vacciner et ils vont contrôler comme les marionnettes avec des fils. d'après les '' ont dit ''...")
28
+ # Output: [{'label': 'opinions', 'score': 0.831]
29
+ ```