Update README.md

README.md

@@ -59,9 +59,18 @@ encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
 model_inputs = encodeds.to(device)
 model.to(device)
 
-generated_ids = model.generate(model_inputs, max_new_tokens=256, do_sample=True)
-decoded = tokenizer.batch_decode(generated_ids)
-print(decoded[0])
+generated_ids = model.generate(
+    model_inputs, # The input to the model
+    max_new_tokens=128, # Limiting the maximum number of new tokens generated
+    do_sample=True, # Enabling sampling to introduce randomness in the generation
+    temperature=0.1, # Setting temperature to control the randomness, lower values make it more deterministic
+    top_p=0.95, # Using nucleus sampling with top-p filtering for more coherent generation       
+    eos_token_id=tokenizer.eos_token_id # Specifying the token that indicates the end of a sequence
+)
+
+decoded_output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+trimmed_output = decoded_output.strip()
+print(decoded_output)
 ```
 
 ## Bias, Risks and Limitations