Transformers How to use FlagAlpha/Llama2-Chinese-13b-Chat with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("question-answering", model="FlagAlpha/Llama2-Chinese-13b-Chat") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("FlagAlpha/Llama2-Chinese-13b-Chat")
model = AutoModelForCausalLM.from_pretrained("FlagAlpha/Llama2-Chinese-13b-Chat", device_map="auto") 
