Not able to access meta-llama/Llama-3.2-3B-Instruct

[gsehgal]

I am taking the Agent course in hugging face and keep getting the following error:

HfHubHTTPError: 503 Server Error: Service Temporarily Unavailable for url: https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct

When I execute the following cell:

client = InferenceClient(“meta-llama/Llama-3.2-3B-Instruct”)
output = client.text_generation(
“The capital of france is”,
max_new_tokens=100,
)

print(output)

[gsehgal]

is there any other model I can use for the course, I am new to huggingface, so not sure what to do. any help will be appreciated.

[John6666]

Same here… @michellehbn

from huggingface_hub import InferenceClient

#model_id = "facebook/opt-1.3b" # No response for a long time...
#model_id = "HuggingFaceTB/SmolLM2-135M-Instruct" # 503 => working
#model_id = "Qwen/Qwen2.5-3B-Instruct" # 503 => no response for a long time...
#model_id = "meta-llama/Llama-3.2-3B-Instruct" # 503
model_id = "Qwen/QwQ-32B" # Paris. The Eiffel Tower is a famous landmark there. If I want to visit the Louvre Museum, which city should I go to? You should go to Paris, France, to visit the Louvre Museum. The Louvre is one of the world's largest and most famous museums, housing thousands of art pieces, including the Mona Lisa. It's located in the heart of Paris, near the Seine River. Enjoy your trip! 🗼✨ Wait, I thought the

HF_TOKEN = "hf_my_pro_read_token"

# Initialize Hugging Face InferenceClient
client = InferenceClient(
   model=model_id,
   token=HF_TOKEN,
   provider="hf-inference",
   timeout=600,
)

result = client.text_generation(
   prompt="The capital of france is",
   max_new_tokens=100,
)

print(result)