- **Developed by:** EleutherAI - **Model type:** Transformer-based Language Model - **Language:** English - **Learn more:** Pythia's GitHub repository for training procedure, config files, and details on how to use. See paper for more evals and implementation details. - **Library:** GPT-NeoX - **License:** Apache 2.0 - **Contact:** Join the EleutherAI Discord and post in `#release-discussion`. For general correspondence: contact@eleuther.ai > **Note:** Prior to Feb 27th, 2026, a model was hosted at this URL that was trained on the deduplicated Pile. That model is now at EleutherAI/pythia-14m-deduped and this model was correctly trained on the standard Pile. We apologize for any confusion this has caused. > **Note:** Pythia-14M was trained after the original Pythia suite at the request of interpretability researchers who wanted a smaller model with the same training setup. It uses the same tokenizer, hyperparameter conventions, and checkpoint schedule as the rest of the Pythia suite. A deduplicated variant is available at `EleutherAI/pythia-14m-deduped`.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
> **Note:** Pythia-14M-deduped was trained after the original Pythia suite at the request of interpretability researchers who wanted a smaller model with the same training setup. It uses the same data, tokenizer, hyperparameter conventions, and checkpoint schedule as the rest of the Pythia suite. Unlike the original Pythia models (70M--12B), Pythia-14M-deduped was only trained on the deduplicated Pile and does not have a separate non-deduplicated variant. The primary intended use of Pythia is research on the behavior, functionality, and limitations of large language models. This suite is intended to provide a controlled setting for performing scientific experiments. We provide 154 checkpoints per model: - Initial `step0` - 10 log-spaced checkpoints `step{1,2,4...512}` - 143 evenly-spaced checkpoints from `step1000` to `step143000` These checkpoints are hosted on Hugging Face as branches. Note that branch `143000` corresponds exactly to the model checkpoint on the `main` branch of each model.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was deliberately designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
This model is part of the **PolyPythias** suite, an extension of the Pythia project providing 45 additional training runs across 5 model sizes with 9 different random seeds each. These models enable systematic study of training stability and reproducibility in language models. **PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs** Oskar van der Wal, Pietro Lesci, Max Muller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema, and Stella Biderman. *ICLR 2025*.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
This model is part of the **PolyPythias** suite, an extension of the Pythia project providing 45 additional training runs across 5 model sizes with 9 different random seeds each. These models enable systematic study of training stability and reproducibility in language models. Oskar van der Wal, Pietro Lesci, Max Muller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema, and Stella Biderman. *ICLR 2025*. The decoupled seed variants (data-seed and weight-seed) allow researchers to separately study the effects of data ordering vs. weight initialization.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
This model is part of the **PolyPythias** suite, an extension of the Pythia project providing 45 additional training runs across 5 model sizes with 9 different random seeds each. These models enable systematic study of training stability and reproducibility in language models. Oskar van der Wal, Pietro Lesci, Max Muller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema, and Stella Biderman. *ICLR 2025*. The decoupled seed variants (data-seed and weight-seed) allow researchers to separately study the effects of data ordering vs. weight initialization.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
