Update app.py

app.py

@@ -2,20 +2,42 @@ import gradio as gr
 import spaces 
 import time 
 import os 
+from transformers import pipeline
+import torch 
+
 key = (os.getenv('API_KEY'))
-from transformers import AutoTokenizer, AutoModelForCausalLM
+model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+
+
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+    token = key
+)
 
-# Utiliser le jeton d'accès API pour charger le modèle
-from transformers import pipeline
 
 messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
     {"role": "user", "content": "Who are you?"},
 ]
-pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3-8B-Instruct", token=key)
-pipe(messages)
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")
+
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
 
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
 
 @spaces.GPU(duration=240)