Update README.md

README.md

@@ -1,14 +1,20 @@
----
-library_name: transformers
-datasets:
-- facebook/xnli
-metrics:
-- accuracy
-base_model:
-- FacebookAI/xlm-roberta-large
----
-
-# XLM-RoBERTa Large finetuned on XNLI
+---
+library_name: transformers
+datasets:
+- facebook/xnli
+metrics:
+- accuracy
+base_model:
+- FacebookAI/xlm-roberta-large
+license: mit
+tags:
+- xlm-roberta
+- finetuning
+- xnli
+- mnli
+---
+
+# XLM-RoBERTa Large finetuned on XNLI dataset
 
 <!-- Provide a quick summary of what the model is/does. -->
 
@@ -16,33 +22,46 @@ base_model:
 
 - **Developed by:** Adrien J.
 - **Model type:** XLM-RoBERTa
-- **Language(s) (NLP):** Multilingual
-- **Finetuned from model:** FacebookAI/xlm-roberta-large
+- **Languages (NLP):** Multilingual
+- **Finetuned from model:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large)
 
 ## How to Get Started
 
-This model is ready-to-use for zero-shot classification.
+This model is ready-to-use for text classification.
 
 ```py
+import pandas as pd
 from transformers import pipeline
 
-# Load a classification pipeline
-classifier = pipeline("text-classification", model="ajayat/xlm-roberta-large-xnli")
-
-# Example input: a pair of premise and hypothesis
-example = dict(
-  premise="A man is eating food.",
-  hypothesis="A man is consuming a meal."
-)
-# Outputs the logits
-result = classifier(example)
+# Load the classification pipeline
+classifier = pipeline("text-classification", "ajayat/xlm-roberta-large-xnli")
+classifier.model.config.id2label = {
+    0: "entailment", 
+    1: "neutral", 
+    2: "contradiction"
+}
+# Example premise and hypothesis
+premise = "A soccer game with multiple males playing."
+hypothesis = "Some men are playing a sport."
+
+# Provide input as a dictionary with text and text_pair keys
+result = classifier({'text': premise, 'text_pair': hypothesis}, top_k=None)
+pd.DataFrame(result)
 ```
 
+|   | label	        | score    |
+|:-:|:-------------:|:--------:|
+| 0 | entailment	| 0.996513 |
+| 1 | neutral	    | 0.003228 |
+| 2 | contradiction	| 0.000260 |
+
 ## Dataset
 
-The [XNLI dataset](https://huggingface.co/datasets/facebook/xnli) (Cross-lingual Natural Language Inference) is a benchmark dataset created by Facebook AI for evaluating cross-lingual understanding. 
-It extends the MultiNLI corpus by translating 7,500 human-annotated English sentence pairs (premise and hypothesis) into 14 languages. 
-Each pair is labeled as entailment, contradiction, or neutral.
+The [XNLI dataset](https://huggingface.co/datasets/facebook/xnli) (Cross-lingual Natural Language Inference) is a benchmark dataset 
+created by Facebook AI for evaluating cross-lingual understanding. 
+It extends the MultiNLI corpus by translating 7,500 human-annotated English sentence pairs (premise and hypothesis) into 14 languages.
+
+Each pair is labeled as `entailment`, `contradiction`, or `neutral`.
 
 ## Training Hyperparameters
 
@@ -68,4 +87,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 - **Hardware Type:** 4x GPUs NVIDIA A100 SXM4 80GB
 - **Hours used:** 7 hours
-- **Compute Region:** France
+- **Compute Region:** France