Update README.md

README.md

@@ -38,7 +38,44 @@ The code to replicate the experiments is available on [GitHub](https://github.co
 
 ## Model Inference
 
-TBA
+To utilize the LlamaLens model for inference, follow these steps:
+
+1. **Install the Required Libraries**:
+
+   Ensure you have the necessary libraries installed. You can do this using pip:
+
+   ```bash
+   pip install transformers torch
+   ```
+2. **Load the Model and Tokenizer:**:
+Use the transformers library to load the LlamaLens model and its tokenizer:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_name = "QCRI/LlamaLens"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+```
+3. **Prepare the Input:**:
+Tokenize your input text:
+```python
+input_text = "Your input text here"
+inputs = tokenizer(input_text, return_tensors="pt")
+```
+4. **Generate the Output:**:
+Generate a response using the model:
+```python
+output = model.generate(**inputs)
+response = tokenizer.decode(output[0], skip_special_tokens=True)
+print(response)
+```
+
+## Paper  
+For an in-depth understanding, refer to our paper: [**LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content**](https://arxiv.org/pdf/2410.15308).
+
+
+
 
 # License
 This model is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).