[HANDS-ON BUG]

[ss1034]

Describe the bug
client.text_generation() throws 503 error every time I use it, however, chat.completion works without any issue

To Reproduce
os.environ["HF_TOKEN"]="my_token"

client = InferenceClient("meta-llama/Llama-3.2-3B-Instruct")

output = client.text_generation(
"The capital of France is",
max_new_tokens=100,
)

print(output)

[ss1034]

Below thing is working: client = InferenceClient(
provider="sambanova",
api_key="my_token",
)

completion = client.chat.completions.create(
model="meta-llama/Llama-3.1-8B-Instruct",
messages=[
{
"role": "user",
"content": "What is the capital of France?"
}
],
max_tokens=512,
)

print(completion.choices[0].message.content)

[Oorgien]

TypeError: InferenceClient.__init__() got an unexpected keyword argument 'provider'

Are you sure that works?