[Bug]: Error generating from LLM: `temperature` (=0.0) has to be a strictly positive float, otherwise your next token scores will be invalid. If you're looking for greedy decoding strategies, set `do_sample=False`.

[komorebi6666]

I use the model on Hugging Face; my config.json file settings for the model are as follows:： "model": {
"provider": "huggingface_pipeline",
"name": "refuelai/Llama-3-Refueled"
}
I executed the following command:：

from autolabel import LabelingAgent, AutolabelDataset
agent = LabelingAgent(config='config.json')
ds = AutolabelDataset('movie_reviews.csv', config = agent.config)
agent.plan(ds)
ds = agent.run(ds)
ds.save('movie_reviews_labeled.csv')

出现问题：
Setting pad_token_id to eos_token_id:128001 for open-end generation.
Setting pad_token_id to eos_token_id:128001 for open-end generation.
Error generating from LLM: temperature (=0.0) has to be a strictly positive float, otherwise your next token scores will be invalid. If you're looking for greedy decoding strategies, set do_sample=False.
━━━━━╸━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/7 0:00:00 -:--:--
Cost in $=0.00Setting pad_token_id to eos_token_id:128001 for open-end generation.

How do I set the corresponding parameters in the config.json file to successfully resolve this issue?