Llama 3.1 8B provides efficient multilingual conversational support ideal for applications where responsiveness and computational efficiency are critical. Effective for building chatbots, automated customer interactions, and applications needing fast yet reliable language understanding.
import openai
import weave
# Weave autopatches OpenAI to log LLM calls to W&B
weave.init("/")
client = openai.OpenAI(# The custom base URL points to W&B Inference
base_url='https://api.inference.wandb.ai/v1',# Get your API key from https://wandb.ai/authorize# Consider setting it in the environment as OPENAI_API_KEY instead for safety
api_key="",# Team and project are required for usage tracking
project="/",)
response = client.chat.completions.create(
model="meta-llama/Llama-3.1-8B-Instruct",
messages=[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"Tell me a joke."}],)print(response.choices[0].message.content)
