From e5e7084e5a2d3525bb9df9facf6d42666b3805db Mon Sep 17 00:00:00 2001 From: Viswanatha Reddy Date: Sat, 3 Feb 2024 01:50:50 -0600 Subject: [PATCH] Update README.md Added paper references. --- README.md | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/README.md b/README.md index 0d672aa9e..7be63c484 100644 --- a/README.md +++ b/README.md @@ -120,3 +120,28 @@ The quantized model is more sensitive to typing / cuda, so it is recommended to ## Evaluation Additional tools for evaluating OLMo models are available at the [OLMo Eval](https://github.com/allenai/ai2-olmo-eval) repo. + + +## References + +1. ``` + @misc{groeneveld2024olmo, + 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 Ananya Harsh 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 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 Hannaneh Hajishirzi}, + year={2024}, + eprint={2402.00838}, + archivePrefix={arXiv}, + primaryClass={cs.CL} + } + ``` +2. ``` + @misc{soldaini2024dolma, + title={Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research}, + author={Luca Soldaini and Rodney Kinney and Akshita Bhagia and Dustin Schwenk and David Atkinson and Russell Authur and Ben Bogin and Khyathi Chandu and Jennifer Dumas and Yanai Elazar and Valentin Hofmann and Ananya Harsh Jha and Sachin Kumar and Li Lucy and Xinxi Lyu and Nathan Lambert and Ian Magnusson and Jacob Morrison and Niklas Muennighoff and Aakanksha Naik and Crystal Nam and Matthew E. Peters and Abhilasha Ravichander and Kyle Richardson and Zejiang Shen and Emma Strubell and Nishant Subramani and Oyvind Tafjord and Pete Walsh and Luke Zettlemoyer and Noah A. Smith and Hannaneh Hajishirzi and Iz Beltagy and Dirk Groeneveld and Jesse Dodge and Kyle Lo}, + year={2024}, + eprint={2402.00159}, + archivePrefix={arXiv}, + primaryClass={cs.CL} + } + ``` +