Llama 3.1 405B Instruct

1import requests
2
3# Replace the empty string with your model id below
4model_id = ""
5baseten_api_key = os.environ["BASETEN_API_KEY"]
6
7messages = [
8    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
9    {"role": "user", "content": "Who are you?"},
10]
11data = {
12    "messages": messages,
13    "stream": True,
14    "max_new_tokens": 512,
15    "temperature": 0.9
16}
17
18# Call model endpoint
19res = requests.post(
20    f"https://model-{model_id}.api.baseten.co/production/predict",
21    headers={"Authorization": f"Api-Key {baseten_api_key}"},
22    json=data,
23    stream=True
24)
25
26# Print the generated tokens as they get streamed 
27for content in res.iter_content():
28    print(content.decode("utf-8"), end="", flush=True)