Transformers How to use ainize/gpt-j-6B-float16 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="ainize/gpt-j-6B-float16") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("ainize/gpt-j-6B-float16")
model = AutoModel.from_pretrained("ainize/gpt-j-6B-float16", device_map="auto") 
