Update README.md

README.md

@@ -8,15 +8,28 @@ pipeline_tag: text-generation
 ---
 # Using NeyabAI:
 
+## Direct Use:
 
-  # Direct Use:
-
+```python
+import torch
+from transformers import GPT2LMHeadModel, GPT2TokenizerFast
 
+model = GPT2LMHeadModel.from_pretrained("XsoraS/NeyabAI")
+tokenizer = GPT2TokenizerFast.from_pretrained("XsoraS/NeyabAI")
+```
+```python
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors='pt') # You can add .to(torch.device("cuda")) to use GPU acceleration.
+    return tokenizer.decode(model.generate(inputs.input_ids, max_length=512, do_sample=True,top_p=0.8, temperature=0.7, num_return_sequences=1,attention_mask=None)[0],skip_special_tokens=True)
 
+prompt = "Hello"
+response = ' '.join(map(str, str(generate_response("### Human: "+prompt+" \n### AI:")).replace("</s>","").split()))
+print(response)
+```
 
-  # Fine-Tuning:
+## Fine-Tuning:
 
-  This repository demonstrates how to fine-tune the NeyabAI(GPT-2) language model on a custom dataset using PyTorch and Hugging Face's Transformers library. The code provides an end-to-end example, from loading the dataset to training the model and evaluating its performance.
+This repository demonstrates how to fine-tune the NeyabAI(GPT-2) language model on a custom dataset using PyTorch and Hugging Face's Transformers library. The code provides an end-to-end example, from loading the dataset to training the model and evaluating its performance.
 
 ## Requirements