Transformers How to use leoclement/llama-2-7b-4bit with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="leoclement/llama-2-7b-4bit") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("leoclement/llama-2-7b-4bit")
model = AutoModel.from_pretrained("leoclement/llama-2-7b-4bit", device_map="auto") 
