from IPython import display 
!pip install transformers==4.14.1 -q
!pip install bitsandbytes-cuda111==0.26.0 -q
!pip install git+https://github.com/aicrumb/transformers-8bit -q

import transformers_8bit

model, tokenizer, config = transformers_8bit.gptj("crumb/gpt-j-6b-finetune-super-glue", device='cuda')

prompt = tokenizer("<QUERY> If birds are in group B, and snakes are in group A, what group are pythons in? <RESPONSE>", return_tensors='pt')
prompt = {key: value.to('cuda') for key, value in prompt.items()}
length = len(prompt['input_ids'][0])
out = model.generate(**prompt, min_length=length+2, max_length=length+2, do_sample=False, pad_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(out[0]))

"""output
<QUERY> If birds are in group B, and snakes are in group A, what group are pythons in? <RESPONSE> Group A
"""