unsloth/Llama-3.1-Nemotron-70B-Instruct-bnb-4bit

[werruww]

colab tpu

from airllm import AutoModel
import torch

MAX_LENGTH = 15

could use hugging face model repo id:

model = AutoModel.from_pretrained("unsloth/Llama-3.1-Nemotron-70B-Instruct-bnb-4bit", delete_original=True)

input_text = [
'What is the capital of United States?',
]

input_tokens = model.tokenizer(input_text,
return_tensors="pt",
return_attention_mask=False,
truncation=True,
max_length=MAX_LENGTH,
padding=False)

generation_output = model.generate(
input_tokens['input_ids'].cuda(),
max_new_tokens=2,
use_cache=True,
return_dict_in_generate=True)

output = model.tokenizer.decode(generation_output.sequences[0])

print(output)

AssertionError: Torch not compiled with CUDA enabled