Bielik-7B-v0.1

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 argparse
import time

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/Bielik-7B-v0.1-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"
    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
    model = model.to(device)
    
    start_time = time.time()
    
    prompt = "Give me a short introduction to large language model."
    inputs = tokenizer(prompt, return_tensors="pt", return_token_type_ids=False).to(device)
    out = model.generate(**inputs, max_new_tokens=80).ravel()
    out = tokenizer.decode(out)
    print(out)
    
    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")
    
if __name__ == "__main__":
    main()

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "speakleash/Bielik-7B-v0.1"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

import torch

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)

import transformers

text = "Najważniejszym celem człowieka na ziemi jest"

pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer)
sequences = pipeline(max_new_tokens=100, do_sample=True, top_k=50, eos_token_id=tokenizer.eos_token_id, text_inputs=text)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

@misc{Bielik7Bv01,
    title     = {Introducing Bielik-7B-v0.1: Polish Language Model},
    author    = {Ociepa, Krzysztof and Flis, Łukasz and Wróbel, Krzysztof and Gwoździej, Adrian and {SpeakLeash Team} and {Cyfronet Team}},
    year      = {2024},
    url       = {https://huggingface.co/speakleash/Bielik-7B-v0.1},
    note      = {Accessed: 2024-04-01}, % change this date
    urldate   = {2024-04-01} % change this date
}

@misc{ociepa2024bielik7bv01polish,
      title={Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation}, 
      author={Krzysztof Ociepa and Łukasz Flis and Krzysztof Wróbel and Adrian Gwoździej and Remigiusz Kinas},
      year={2024},
      eprint={2410.18565},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.18565}, 
}