Duplicated from thegovind/blink-4b
How to use DollasAndSpence/blink-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="DollasAndSpence/blink-4b")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DollasAndSpence/blink-4b") model = AutoModelForCausalLM.from_pretrained("DollasAndSpence/blink-4b", device_map="auto")
