Skip to content

Latest commit

 

History

History
140 lines (108 loc) · 9.43 KB

README.md

File metadata and controls

140 lines (108 loc) · 9.43 KB
Raw
OLMo Logo

OLMo: Open Language Model

GitHub License GitHub release Paper URL

OLMo is a repository for training and using AI2's state-of-the-art open language models. It is designed by scientists, for scientists.

Installation

First, install PyTorch following the instructions specific to your operating system.

For training and fine-tuning, we recommend installing from source:

git clone https://github.com/allenai/OLMo.git
cd OLMo
pip install -e .[all]

You can also install from PyPI with:

pip install ai2-olmo

Models

Overview

OLMo pretraining follows a two-stage training procedure. In the first stage, we train on large amounts of mostly web-based data: OLMo-mix-1124 In the second stage, we train on a smaller amount of high-quality, targeted data: Dolmino-mix-1124

You can find all the checkpoints, at minimum every 1000 training steps, on Huggingface:

Stage 1

To get the tokenized training data, look at the paths in the training configs. To reproduce at large scale, we recommend downloading the files locally and changing the paths to point to your local file system, for performance reasons.

OLMo2 7B OLMo2 13B
Number of tokens 4 Trillion 5 Trillion
Checkpoint stage1-step928646-tokens3896B stage1-step596057-tokens5001B
Training config OLMo2-7B-stage1.yaml OLMo2-13B-stage1.yaml
WandB wandb.ai/…/OLMo2-7B (link to come) wandb.ai/…/OLMo2-13B (link to come)

Stage 2 for the 7B

For the 7B model, we train three times with different data order on 50B high quality tokens, and then average ("soup") the models.

Checkpoint Training config WandB
random seed 42 stage2-ingredient1-step11931-tokens50B link to come
random seed 42069 stage2-ingredient2-step11931-tokens50B link to come
random seed 666 stage2-ingredient3-step11931-tokens50B link to come
final souped model main link to come

Stage 2 for the 13B

For the 13B model, we train three times with different data order on 100B high quality tokens, and one more time on 300B high quality tokens. Then we average ("soup") the models.

Checkpoint Training config WandB
random seed 1110, 100B stage2-ingredient1-step11931-tokens100B link to come
random seed 2662, 100B stage2-ingredient2-step11931-tokens100B link to come
random seed 6209, 100B stage2-ingredient3-step11931-tokens100B link to come
random seed 2662, 300B stage2-ingredient4-step11931-tokens300B link to come
final souped model main link to come

Instruction tuned variants

For instruction tuned variants of these models, go to

Inference

You can use our Hugging Face integration to run inference on the OLMo Transformers checkpoints:

from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B")
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-1124-7B")
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])

Alternatively, with the Hugging Face pipeline abstraction:

from transformers import pipeline
olmo_pipe = pipeline("text-generation", model="allenai/OLMo-2-1124-7B")
print(olmo_pipe("Language modeling is"))

Quantization

olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B", torch_dtype=torch.float16, load_in_8bit=True)  # requires bitsandbytes

The quantized model is sensitive to input types and CUDA handling. To avoid potential issues, we recommend explicitly converting input IDs to CUDA using: inputs.input_ids.to('cuda')

Evaluation

Additional tools for evaluating OLMo models are available at the OLMo Eval repo.

Citing

@article{OLMo,
  title={OLMo: Accelerating the Science of Language Models},
  author={Dirk Groeneveld and Iz Beltagy and Pete Walsh and Akshita Bhagia and Rodney Kinney and Oyvind Tafjord and A. Jha and Hamish Ivison and Ian Magnusson and Yizhong Wang and Shane Arora and David Atkinson and Russell Authur and Khyathi Raghavi Chandu and Arman Cohan and Jennifer Dumas and Yanai Elazar and Yuling Gu and Jack Hessel and Tushar Khot and William Merrill and Jacob Daniel Morrison and Niklas Muennighoff and Aakanksha Naik and Crystal Nam and Matthew E. Peters and Valentina Pyatkin and Abhilasha Ravichander and Dustin Schwenk and Saurabh Shah and Will Smith and Emma Strubell and Nishant Subramani and Mitchell Wortsman and Pradeep Dasigi and Nathan Lambert and Kyle Richardson and Luke Zettlemoyer and Jesse Dodge and Kyle Lo and Luca Soldaini and Noah A. Smith and Hanna Hajishirzi},
  year={2024},
  url={https://api.semanticscholar.org/CorpusID:267365485},
  journal={arXiv preprint},
}