I keep receiving 503 error when using HuggingFaceEndpoint to access the model
Here're my codes:
import os
import warnings
from urllib3.exceptions import NotOpenSSLWarning
from langchain_huggingface import HuggingFaceEndpoint
import sys
warnings.filterwarnings("ignore", category=NotOpenSSLWarning)
os.environ["HUGGINGFACEHUB_API_TOKEN"] = '....'
llm = HuggingFaceEndpoint(
repo_id="meta-llama/Llama-3.2-3B-Instruct",
timeout=60
)
def explain_code(code):
base_prompt = """
Tell me about the flower
"""
prompt = base_prompt + code
completion = llm.invoke(prompt)
return completion
if name == "main":
code = """rose"""
result = explain_code(code)
print(result)
But I got the error as follows:
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 503 Server Error: Service Temporarily Unavailable for url: https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct
Please could someone tell me how to fix the problem?
Thanks!!!
me too
Please could someone tell me how to fix it? Or is there any available Llama model that I can replace with? I'm struggling under a deadline...
Please could someone tell me how to fix it? Or is there any available Llama model that I can replace with? I'm struggling under a deadline...
Just change to:client = InferenceClient("meta-llama/Llama-3.1-8B-Instruct")
