RuntimeError: You must initialize the accelerate state by calling either `PartialState()` or `Accelerator()` before using the logging utility.
#7
by amarrrv - opened
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="HuggingFaceH4/starchat-beta", torch_dtype=torch.bfloat16, device_map="auto")
# We use a variant of ChatML to format each message
prompt_template = "<|system|>\n<|end|>\n<|user|>\n{query}<|end|>\n<|assistant|>"
prompt = prompt_template.format(query="How do I sort a list in Python?")
# We use a special <|end|> token with ID 49155 to denote ends of a turn
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2, top_k=50, top_p=0.95, eos_token_id=49155)
I am trying to run the above code on Google Colab. I get the following errorRuntimeError: You must initialize the accelerate state by calling either `PartialState()` or `Accelerator()` before using the logging utility.
The error is generated for the last line
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2, top_k=50, top_p=0.95, eos_token_id=49155)
Any suggestions on how I can debug and resolve this ?