OLMo 7B 2024年4月版模型卡片

olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-0424-hf", revision="step1000-tokens4B")

from huggingface_hub import list_repo_refs
out = list_repo_refs("allenai/OLMo-7B-0424-hf")
branches = [b.name for b in out.branches]

from openmind import pipeline, is_torch_npu_available
from openmind import AutoTokenizer, AutoModelForCausalLM
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
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/OLMo-1.7-7B-hf-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).to(device)
    
    start_time = time.time()
    text = "Generative AI is "
    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer,device=device)
    generated_text = pipe(text, max_length=50, do_sample=False, no_repeat_ngram_size=2)[0]
    print(generated_text['generated_text'])
    
    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 AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-0424-hf")
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-7B-0424-hf")
message = ["Language modeling is"]
inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
# optional verifying cuda
# inputs = {k: v.to('cuda') for k,v in inputs.items()}
# olmo = olmo.to('cuda')
response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
>> 'Language modeling is the first step to build natural language generation...'

from transformers import pipeline
olmo_pipe = pipeline("text-generation", model="allenai/OLMo-7B-0424-hf")
print(olmo_pipe("Language modeling is "))
>> 'Language modeling is a branch of natural language processing that aims to...'

torchrun --nproc_per_node=8 scripts/train.py {path_to_train_config} \
    --data.paths=[{path_to_data}/input_ids.npy] \
    --data.label_mask_paths=[{path_to_data}/label_mask.npy] \
    --load_path={path_to_checkpoint} \
    --reset_trainer_state

@article{Groeneveld2023OLMo,
  title={OLMo: Accelerating the Science of Language Models},
  author={Groeneveld, Dirk and Beltagy, Iz and Walsh, Pete and Bhagia, Akshita and Kinney, Rodney and Tafjord, Oyvind and Jha, Ananya Harsh and Ivison, Hamish and Magnusson, Ian and Wang, Yizhong and Arora, Shane and Atkinson, David and Authur, Russell and Chandu, Khyathi and Cohan, Arman and Dumas, Jennifer and Elazar, Yanai and Gu, Yuling and Hessel, Jack and Khot, Tushar and Merrill, William and Morrison, Jacob and Muennighoff, Niklas and Naik, Aakanksha and Nam, Crystal and Peters, Matthew E. and Pyatkin, Valentina and Ravichander, Abhilasha and Schwenk, Dustin and Shah, Saurabh and Smith, Will and Subramani, Nishant and Wortsman, Mitchell and Dasigi, Pradeep and Lambert, Nathan and Richardson, Kyle and Dodge, Jesse and Lo, Kyle and Soldaini, Luca and Smith, Noah A. and Hajishirzi, Hannaneh},
  journal={Preprint},
  year={2024}
}