OLMo 1B July 2024 is the latest version of the original OLMo 1B model rocking a 4.4 point increase in HellaSwag, among other evaluations improvements, from an improved version of the Dolma dataset and staged training. This version is for direct use with HuggingFace Transformers from v4.40 on.
OLMo is a series of Open Language Models designed to enable the science of language models. The OLMo models are trained on the Dolma dataset. We release all code, checkpoints, logs, and details involved in training these models.
Supported by: Databricks, Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University, AMD, CSC (Lumi Supercomputer), UW
Model type: a Transformer style autoregressive language model.
Language(s) (NLP): English
License: The code and model are released under Apache 2.0.
Contact: Technical inquiries: olmo at allenai dot org. Press: press at allenai dot org
Date cutoff: Oct. 2023, with most data from Feb./March 2023 based on Dolma dataset version.
Install Transformers. Then proceed as usual with HuggingFace:
from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-1B-0724-hf")
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-1B-0724-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...'
Alternatively, with the pipeline abstraction:
from transformers import pipeline
olmo_pipe = pipeline("text-generation", model="allenai/OLMo-1B-0724-hf")
print(olmo_pipe("Language modeling is "))
>> 'Language modeling is a branch of natural language processing that aims to...'
Or, you can make this slightly faster by quantizing the model, e.g. AutoModelForCausalLM.from_pretrained("allenai/OLMo-1B-0724-hf", torch_dtype=torch.float16, load_in_8bit=True) (requires bitsandbytes). The quantized model is more sensitive to typing / cuda, so it is recommended to pass the inputs as inputs.input_ids.to('cuda') to avoid potential issues.
Model fine-tuning can be done from the final checkpoint (the main revision of this model) or many intermediate checkpoints. Two recipes for tuning are available.
\*Unlike OLMo, Pythia, and TinyLlama, StabilityAI has not disclosed yet the data StableLM was trained on, making comparisons with other efforts challenging.
For training data details, please see the Dolma documentation. This model uses the new 1.7 version with more data sources, better deduplication, and quality filtering. During the annealing phase we use a higher quality subset of Dolma with a linearly decaying learning rate to 0.
In contrast to the first OLMo, we trained OLMo 7B 0424 with a two-stage curriculum:
In the first stage, we trained the model from scratch on the Dolma 1.7 dataset. We set a cosine learning rate schedule with a warmup of 2500 steps, a peak learning rate of 3e-4, and a cosine decay to 3e-5 after 3T tokens. We cut off this stage after 2T tokens, when the learning rate is still high.
At this point we switch to the second stage, in which we train on a higher-quality subset of Dolma 1.7 (see below) for another 50B tokens, while linearly decaying the learning rate to 0. Our high-quality subset includes (1) using all available Wikipedia, OpenWebMath and Flan data, (2) removing Dolma CC, CC News, and Megawika, and (3) rebalancing remaining sources to achieve approximately equal proportions of each. See exact token counts and relative proportions of this second stage mix below.
Both stages contribute equally to the final performance of the OLMo model. After the first stage, OLMo 7B 0424 already outperforms the older OLMo. The second stage consistently adds 2 to 3 points of performance on top.
OLMo 7B variants were either trained on MI250X GPUs at the LUMI supercomputer, or A100-40GB GPUs provided by MosaicML. A summary of the environmental impact. Further details are available in the paper.
Like any base language model or fine-tuned model without safety filtering, it is relatively easy for a user to prompt these models to generate harmful and generally sensitive content. Such content can also be produced unintentionally, especially in the case of bias, so we recommend users consider the risks of applications of this technology.
Otherwise, many facts from OLMo or any LLM will often not be true, so they should be checked.
@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}
}
APA:
Groeneveld, D., Beltagy, I., Walsh, P., Bhagia, A., Kinney, R., Tafjord, O., Jha, A., Ivison, H., Magnusson, I., Wang, Y., Arora, S., Atkinson, D., Authur, R., Chandu, K., Cohan, A., Dumas, J., Elazar, Y., Gu, Y., Hessel, J., Khot, T., Merrill, W., Morrison, J., Muennighoff, N., Naik, A., Nam, C., Peters, M., Pyatkin, V., Ravichander, A., Schwenk, D., Shah, S., Smith, W., Subramani, N., Wortsman, M., Dasigi, P., Lambert, N., Richardson, K., Dodge, J., Lo, K., Soldaini, L., Smith, N., & Hajishirzi, H. (2024). OLMo: Accelerating the Science of Language Models. Preprint.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("allenai/OLMo-1B-0724-hf", revision="d7cbab742d80589e714b1a2d7f838dcd21cbe143")
model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-1B-0724-hf", revision="d7cbab742d80589e714b1a2d7f838dcd21cbe143", device_map="auto")
allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject: 
