Update README.md

README.md

@@ -12,36 +12,11 @@ libraries:
 # Model Name
 
 ## Model Description
+The model is a roberta-base fine-tuned on various social media dataset and Wikipedia dataset. 
+The model takes a news article and predicts if it is true or fake.
+The format of the input should be:
 
-Describe the overall purpose and capabilities of the model here. Explain what the model does and its intended tasks. For instance, this model is designed to assist in educational and learning activities by providing text-based responses or solutions.
+```
+<title> TITLE HERE <content> CONTENT HERE <end>
 
-## Model Architecture
-
-Detail the architecture of the model, including the type of model (e.g., BERT, GPT) and any significant modifications or configurations applied to the original architecture.
-
-## Training Data
-
-Describe the dataset(s) used for training the model. Mention the source of the data, the data type, and how it was processed or transformed before training. Discuss the size of the training set and any balancing techniques used if applicable.
-
-## Intended Use
-
-Explain the intended use cases for the model. Describe the target audience and the scenarios in which the model is expected to perform well. This could include educational tools, tutoring systems, or other learning assistance platforms.
-
-## Limitations and Biases
-
-Acknowledge any limitations or biases in the model. Discuss aspects such as data limitations, potential biases in training data, or expected areas where the model may not perform optimally.
-
-## How to Use
-
-Provide examples of how to use the model with the Hugging Face Transformers library. Include code snippets for initializing the model, loading it, and making predictions.
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-tokenizer = AutoTokenizer.from_pretrained("your-model-name")
-model = AutoModelForCausalLM.from_pretrained("your-model-name")
-
-text = "Your prompt here"
-encoded_input = tokenizer(text, return_tensors='pt')
-output = model.generate(**encoded_input)
-print(tokenizer.decode(output[0], skip_special_tokens=True))
+```