from openmind import AutoTokenizer, AutoModelForCausalLM, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/gpt-neo-125m-openmind",
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
        
    model = model_path
    tokenizer = AutoTokenizer.from_pretrained(model)
    pipeline = openmind.pipeline(
        "text-generation",
        model=model,
        torch_dtype=torch.float16,
        device_map="auto",
    )

    sequences = pipeline(
        'EleutherAI has',
        do_sample=True,
        top_k=10,
        num_return_sequences=1,
        repetition_penalty=1.5,
        eos_token_id=tokenizer.eos_token_id,
        max_length=500,
    )
    for seq in sequences:
        print(f"Result: {seq['generated_text']}")
    
if __name__ == "__main__":
    main()

@software{gpt-neo,

  author       = {Black, Sid and
                  Leo, Gao and
                  Wang, Phil and
                  Leahy, Connor and
                  Biderman, Stella},
  title        = {{GPT-Neo: Large Scale Autoregressive Language 
                   Modeling with Mesh-Tensorflow}},
  month        = mar,
  year         = 2021,
  note         = {{If you use this software, please cite it using 
                   these metadata.}},
  publisher    = {Zenodo},
  version      = {1.0},
  doi          = {10.5281/zenodo.5297715},
  url          = {https://doi.org/10.5281/zenodo.5297715}
}

@article{gao2020pile,
  title={The Pile: An 800GB Dataset of Diverse Text for Language Modeling},
  author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and others},
  journal={arXiv preprint arXiv:2101.00027},
  year={2020}
}