print("huggingface")
access_token = 'xxxxx'
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b", token = access_token)
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", token = access_token)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print("outputs =", outputs)
print(tokenizer.decode(outputs[0]))
There’s no output past “huggingface” - it just finishes off and returns back to the terminal.