Update README.md

README.md

@@ -3,6 +3,7 @@ tags: autotrain
 language: en
 widget:
 - text: "I love AutoTrain 🤗"
+- Output: "Positive"
 datasets:
 - Souvikcmsa/autotrain-data-sentiment_analysis
 co2_eq_emissions: 0.029363397844935534
@@ -10,12 +11,10 @@ co2_eq_emissions: 0.029363397844935534
 
 # Model Trained Using AutoTrain
 
-- Problem type: Multi-class Classification
-- Model ID: 762923428
-- CO2 Emissions (in grams): 0.029363397844935534
+- Problem type: Multi-class Classification (3-class Sentiment Classification)
 
 ## Validation Metrics
-
+If you search sentiment analysis model in huggingface you find a model from finiteautomata. Their model provides micro and macro F1 score around 67%. Check out this model with around 80% of macro and micro F1 score. 
 - Loss: 0.4992932379245758
 - Accuracy: 0.799017824663514
 - Macro F1: 0.8021508522962549
@@ -49,4 +48,12 @@ tokenizer = AutoTokenizer.from_pretrained("Souvikcmsa/autotrain-sentiment_analys
 inputs = tokenizer("I love AutoTrain", return_tensors="pt")
 
 outputs = model(**inputs)
+```
+OR
+```
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model = "Souvikcmsa/BERT_sentiment_analysis")
+classifier("I loved Star Wars so much!")# Positive
+classifier("A soccer game with multiple males playing. Some men are playing a sport.")# Neutral
 ```