Update README.md

README.md

@@ -75,7 +75,41 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+Inference Code:
+
+```
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+# Load fine-tuned GPT-2 model and tokenizer
+model = GPT2LMHeadModel.from_pretrained("AIGym/TinyGPT2-81M-colab") # or change the name to the checkpoint if you wanted to try them out
+tokenizer = GPT2Tokenizer.from_pretrained("AIGym/TinyGPT2-81M-colab") # use the same as the one above unless you know what you are doing
+
+# Example prompts
+prompts = [
+    "Artificial intelligence is",
+    "The future of humanity depends on",
+    "In a galaxy far, far away, there lived",
+    "To be or not to be, that is",
+    "Once upon a time, there was a"
+]
+
+# Function to generate text based on a prompt
+def generate_text(prompt, max_length=120, temperature=0.3):
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    attention_mask = torch.ones(input_ids.shape, dtype=torch.long)
+    output = model.generate(input_ids, attention_mask=attention_mask, max_length=max_length, temperature=temperature, num_return_sequences=1)
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    return generated_text
+
+# Generate and print completions for each prompt
+for prompt in prompts:
+    completion = generate_text(prompt)
+    print("Prompt:", prompt)
+    print("Completion:", completion)
+    print()
+```
+
 
 ## Training Details