Update README.md

README.md

@@ -308,11 +308,11 @@ Where to send questions or comments about the model Instructions on how to provi
 
 ## How to use
 
-This repository for use with `[CTranslate2](https://github.com/OpenNMT/CTranslate2)`.
+This repository for use with [CTranslate2](https://github.com/OpenNMT/CTranslate2).
 
 ### Use with CTranslate2
 
-This example code is obtained from [CTranslate2_transformers](https://opennmt.net/CTranslate2/guides/transformers.html#mpt). 
+This example code is obtained from [CTranslate2_transformers](https://opennmt.net/CTranslate2/guides/transformers.html#mpt) and [tokenizer AutoTokenizer](https://huggingface.co/docs/transformers/main_classes/tokenizer).  
 More detailed information about the `generate_batch` methon can be found at [CTranslate2_Generator.generate_batch](https://opennmt.net/CTranslate2/python/ctranslate2.Generator.html#ctranslate2.Generator.generate_batch).
 
 ```python
@@ -320,14 +320,31 @@ import ctranslate2
 import transformers
 
 model_id = "avans06/Meta-Llama-3-8B-Instruct-ct2-int8_float16"
-generator = ctranslate2.Generator(model_id, device="auto", compute_type="int8_float16")
+model = ctranslate2.Generator(model_id, device="auto", compute_type="int8_float16")
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 
-prompt = "What is the meaning of Large language model?"
-input_tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt))
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
 
-results = generator.generate_batch([input_tokens], include_prompt_in_result=False)
+input_ids = tokenizer.apply_chat_template(
+    messages, 
+    tokenize=False, 
+    add_generation_prompt=True
+)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+input_tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(input_ids))
+
+results = model.generate_batch([input_tokens], include_prompt_in_result=False, max_length=256, sampling_temperature=0.6, sampling_topp=0.9, end_token=terminators)
 output = tokenizer.decode(results[0].sequences_ids[0])
+
+print(output)
 ```
 
 ## Hardware and Software