{"payload":{"pageCount":3,"repositories":[{"type":"Public","name":"lm-evaluation-harness","owner":"EleutherAI","isFork":false,"description":"A framework for few-shot evaluation of language models.","topicNames":["transformer","language-model","evaluation-framework"],"topicsNotShown":0,"allTopics":["transformer","language-model","evaluation-framework"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":63,"issueCount":196,"starsCount":5315,"forksCount":1384,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-23T15:58:16.083Z"}},{"type":"Public","name":"concept-erasure","owner":"EleutherAI","isFork":false,"description":"Erasing concepts from neural representations with provable guarantees","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":2,"starsCount":194,"forksCount":15,"license":"MIT License","participation":[0,7,3,0,4,2,0,0,3,2,0,1,2,5,1,1,7,0,2,4,1,0,0,0,0,0,0,0,0,0,0,0,3,0,4,3,0,0,0,0,0,0,0,0,0,0,2,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-23T05:15:19.958Z"}},{"type":"Public","name":"gpt-neox","owner":"EleutherAI","isFork":false,"description":"An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries","topicNames":["transformers","language-model","gpt-3","deepspeed-library"],"topicsNotShown":0,"allTopics":["transformers","language-model","gpt-3","deepspeed-library"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":27,"issueCount":54,"starsCount":6627,"forksCount":961,"license":"Apache License 2.0","participation":[2,5,0,3,7,6,3,2,1,0,1,2,1,1,0,1,12,7,8,0,1,1,6,4,0,2,0,4,0,3,17,0,5,2,2,3,2,1,2,5,7,9,2,4,3,0,0,1,1,5,1,5],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-22T12:34:59.137Z"}},{"type":"Public","name":"aria-amt","owner":"EleutherAI","isFork":false,"description":"Efficient and robust implementation of seq-to-seq automatic piano transcription.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":0,"starsCount":6,"forksCount":4,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-17T18:42:26.010Z"}},{"type":"Public","name":"aria","owner":"EleutherAI","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":0,"starsCount":36,"forksCount":6,"license":"Apache License 2.0","participation":[1,1,1,3,1,0,0,1,2,0,8,8,2,0,0,0,0,0,8,9,4,2,3,9,2,1,0,6,3,8,1,0,0,1,4,8,1,2,2,2,1,3,0,0,0,0,0,1,0,0,1,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-14T14:28:07.342Z"}},{"type":"Public","name":"w2s","owner":"EleutherAI","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":0,"forksCount":0,"license":"MIT License","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,25,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-22T23:17:03.576Z"}},{"type":"Public","name":"weak-to-strong","owner":"EleutherAI","isFork":true,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":2,"starsCount":6,"forksCount":291,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-10T17:59:25.843Z"}},{"type":"Public","name":"cookbook","owner":"EleutherAI","isFork":false,"description":"Deep learning for dummies. All the practical details and useful utilities that go into working with real models.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":6,"starsCount":184,"forksCount":13,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-09T14:21:52.315Z"}},{"type":"Public","name":"features-across-time","owner":"EleutherAI","isFork":false,"description":"Understanding how features learned by neural networks evolve throughout training","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":25,"forksCount":1,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-23T14:28:52.921Z"}},{"type":"Public","name":"cupbearer","owner":"EleutherAI","isFork":true,"description":"A library for mechanistic anomaly detection","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":3,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-23T06:56:23.122Z"}},{"type":"Public","name":"elk","owner":"EleutherAI","isFork":false,"description":"Keeping language models honest by directly eliciting knowledge encoded in their activations.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":10,"issueCount":13,"starsCount":171,"forksCount":32,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-13T17:32:50.997Z"}},{"type":"Public","name":"DeeperSpeed","owner":"EleutherAI","isFork":true,"description":"DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":159,"forksCount":3898,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-22T07:31:01.226Z"}},{"type":"Public","name":"improved-t5","owner":"EleutherAI","isFork":false,"description":"Experiments for efforts to train a new and improved t5","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":75,"forksCount":5,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-15T05:51:48.509Z"}},{"type":"Public","name":"elk-generalization","owner":"EleutherAI","isFork":false,"description":"Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from easy questions to hard","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":21,"forksCount":3,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-11T17:19:58.706Z"}},{"type":"Public","name":"variance-across-time","owner":"EleutherAI","isFork":false,"description":"Studying the variance in neural net predictions across training time","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":3,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-24T07:12:33.410Z"}},{"type":"Public","name":"tuned-lens","owner":"EleutherAI","isFork":true,"description":"Tools for understanding how transformer predictions are built layer-by-layer","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":2,"forksCount":36,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-26T09:40:53.155Z"}},{"type":"Public","name":"math-lm","owner":"EleutherAI","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":9,"starsCount":991,"forksCount":74,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-12T05:10:40.751Z"}},{"type":"Public","name":"bayesian-adam","owner":"EleutherAI","isFork":false,"description":"Exactly what it says on the tin","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-04T19:09:06.375Z"}},{"type":"Public","name":"RWKV-LM","owner":"EleutherAI","isFork":true,"description":"RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, \"infinite\" ctx_len, and free sentence embedding.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":808,"license":"Apache License 2.0","participation":[1,0,0,2,2,2,2,0,8,1,3,0,1,3,4,7,8,3,0,1,6,0,3,1,1,1,0,0,6,14,0,1,0,0,2,1,4,6,5,0,0,0,0,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-21T10:01:35.441Z"}},{"type":"Public","name":"ccs","owner":"EleutherAI","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":1,"starsCount":3,"forksCount":6,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-09T19:09:34.568Z"}},{"type":"Public","name":"TransformerEngine","owner":"EleutherAI","isFork":true,"description":"A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":229,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-08T00:03:06.388Z"}},{"type":"Public","name":"alignment-handbook","owner":"EleutherAI","isFork":true,"description":"Robust recipes for to align language models with human and AI preferences","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":3,"forksCount":330,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-22T15:16:19.743Z"}},{"type":"Public","name":"classifier-latent-diffusion","owner":"EleutherAI","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-06T08:58:18.144Z"}},{"type":"Public","name":"stackexchange-dataset","owner":"EleutherAI","isFork":false,"description":"Python tools for processing the stackexchange data dumps into a text dataset for Language Models","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":1,"starsCount":65,"forksCount":15,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-06T00:30:43.083Z"}},{"type":"Public","name":"best-download","owner":"EleutherAI","isFork":false,"description":"URL downloader supporting checkpointing and continuous checksumming.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":1,"starsCount":19,"forksCount":7,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-29T10:39:17.947Z"}},{"type":"Public","name":"github-downloader","owner":"EleutherAI","isFork":true,"description":"Script for downloading GitHub.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":5,"issueCount":0,"starsCount":84,"forksCount":42,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-15T08:59:01.744Z"}},{"type":"Public","name":"prefix-free-tokenizer","owner":"EleutherAI","isFork":false,"description":"A prefix free tokenizer","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-06T18:38:59.367Z"}},{"type":"Public archive","name":"truncated-gaussian","owner":"EleutherAI","isFork":false,"description":"Method-of-moments estimation and sampling for truncated multivariate Gaussian distributions","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-23T08:25:01.750Z"}},{"type":"Public","name":"latent-video-diffusion","owner":"EleutherAI","isFork":false,"description":"Latent video diffusion","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":4,"forksCount":7,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-04T16:43:57.723Z"}},{"type":"Public","name":"mdl","owner":"EleutherAI","isFork":false,"description":"Minimum Description Length probing for neural network representations","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":15,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-09-30T05:22:22.193Z"}}],"repositoryCount":87,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}