Update README.md

README.md

@@ -68,6 +68,42 @@ Our work can be cited as:
 
 This model is a Chat model, that is, it is finetuned for Chat function and works best with the provided template.
 
+#### With pipeline
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+
+model_name = "croissantllm/CroissantLLMChat-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+
+messages = [
+   {"role": "user", "content": "Qui est le président francais ?"},
+]
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+)
+
+generation_args = {
+    "max_new_tokens": 500,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+output = pipe(messages, **generation_args)
+print(output[0]['generated_text'])
+```
+
+#### With generate
+
+This might require a stopping criteria on <|im_end|> token.
+
 ```python
 
 import torch