Transformers How to use MMEX/quantized_superhot_wizardLM_13b_v1.1 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="MMEX/quantized_superhot_wizardLM_13b_v1.1", trust_remote_code=True) # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("MMEX/quantized_superhot_wizardLM_13b_v1.1", trust_remote_code=True)
model = AutoModel.from_pretrained("MMEX/quantized_superhot_wizardLM_13b_v1.1", trust_remote_code=True, device_map="auto") 
