| | The Practitioner's Guide to the Maximal Update Parameterization (eleuther.ai) |
|
1 point by tipsytoad 16 days ago | past
|
| | Experiments in Weak-to-Strong Generalization (eleuther.ai) |
|
1 point by veryluckyxyz 3 months ago | past
|
| | Pile-T5 (eleuther.ai) |
|
59 points by tosh 5 months ago | past | 15 comments
|
| | Yi-34B, Llama 2, and common practices in LLM training (eleuther.ai) |
|
41 points by helloericsf 6 months ago | past | 3 comments
|
| | The Pile is a 825 GiB diverse, open-source language modelling data set (2020) (eleuther.ai) |
|
332 points by bilsbie 7 months ago | past | 234 comments
|
| | The Foundation Model Development Cheatsheet (eleuther.ai) |
|
2 points by mellosouls 7 months ago | past
|
| | Llemma: An Open Language Model for Mathematics (eleuther.ai) |
|
3 points by camjohnson26 11 months ago | past | 1 comment
|
| | EleutherAI: Empowering Open-Source Artificial Intelligence Research (eleuther.ai) |
|
1 point by charlysl on July 11, 2023 | past
|
| | Minetester: A fully open RL environment built on Minetest (eleuther.ai) |
|
7 points by b_mc2 on July 9, 2023 | past | 3 comments
|
| | The Pile (eleuther.ai) |
|
1 point by tosh on May 1, 2023 | past
|
| | The Pile (eleuther.ai) |
|
1 point by tosh on April 19, 2023 | past
|
| | Basic math related to computation and memory usage for transformers (eleuther.ai) |
|
168 points by tim_sw on April 19, 2023 | past | 13 comments
|
| | Exploratory Analysis of TRLX RLHF Transformers with TransformerLens (eleuther.ai) |
|
3 points by tim_sw on April 3, 2023 | past
|
| | EleutherAI announces it has become a non-profit (eleuther.ai) |
|
259 points by stellaathena on March 2, 2023 | past | 105 comments
|
| | Announcing GPT-NeoX-20B (eleuther.ai) |
|
200 points by jscob on Feb 2, 2022 | past | 70 comments
|
| | Played with Free GPT-J to outline building an app, should devs worry? (eleuther.ai) |
|
2 points by sharemywin on Sept 16, 2021 | past | 3 comments
|
| | Why Release a Large Language Model? (eleuther.ai) |
|
1 point by danboarder on Aug 10, 2021 | past
|
| | EleutherAI One Year Retrospective (eleuther.ai) |
|
142 points by tehsauce on July 8, 2021 | past | 43 comments
|
| | GPT-J-6B (eleuther.ai) |
|
2 points by weinzierl on June 25, 2021 | past
|
| | Why Release a Large Language Model? (eleuther.ai) |
|
2 points by btdmaster on June 24, 2021 | past
|
| | Eleuther GPT-J-6B web demo (eleuther.ai) |
|
1 point by burgalon on June 10, 2021 | past
|
| | Rotary Embeddings: A Relative Revolution (eleuther.ai) |
|
6 points by asparagui on April 21, 2021 | past | 1 comment
|
| | Rotary Embeddings: A Relative Revolution (eleuther.ai) |
|
1 point by bratao on April 21, 2021 | past
|
| | Eluther: A grassroots collective of researchers working to open source AI (eleuther.ai) |
|
1 point by Balgair on March 31, 2021 | past
|
| | EleutherAI Grassroots AI Research (eleuther.ai) |
|
2 points by sieste on Jan 18, 2021 | past
|
| | GPT-Neo – Building a GPT-3-sized model, open source and free (eleuther.ai) |
|
725 points by sieste on Jan 18, 2021 | past | 252 comments
|
| | [dupe] The Pile: An 800GB Dataset of Diverse Text for Language Modeling [pdf] (eleuther.ai) |
|
1 point by nixtaken on Jan 11, 2021 | past | 1 comment
|
| | The Pile: An 800GB Dataset of Diverse Text for Language Modeling (eleuther.ai) |
|
223 points by leogao on Jan 1, 2021 | past | 60 comments
|