{"id":22359930,"url":"https://github.com/qinyao-he/bit-rnn","last_synced_at":"2025-07-30T12:32:38.747Z","repository":{"id":88885659,"uuid":"74811558","full_name":"qinyao-he/bit-rnn","owner":"qinyao-he","description":"Quantize weights and activations in Recurrent Neural Networks.","archived":false,"fork":false,"pushed_at":"2018-07-27T23:45:26.000Z","size":26,"stargazers_count":94,"open_issues_count":0,"forks_count":30,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-04-06T08:11:32.606Z","etag":null,"topics":["language-model","lowbit-neural-network","paper","recurrent-neural-networks","tensorflow"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1611.10176","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/qinyao-he.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-11-26T07:30:49.000Z","updated_at":"2025-01-21T03:56:01.000Z","dependencies_parsed_at":"2023-06-13T00:20:38.321Z","dependency_job_id":null,"html_url":"https://github.com/qinyao-he/bit-rnn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/qinyao-he/bit-rnn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qinyao-he%2Fbit-rnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qinyao-he%2Fbit-rnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qinyao-he%2Fbit-rnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qinyao-he%2Fbit-rnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/qinyao-he","download_url":"https://codeload.github.com/qinyao-he/bit-rnn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qinyao-he%2Fbit-rnn/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267867803,"owners_count":24157357,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-30T02:00:09.044Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["language-model","lowbit-neural-network","paper","recurrent-neural-networks","tensorflow"],"created_at":"2024-12-04T15:28:13.068Z","updated_at":"2025-07-30T12:32:38.733Z","avatar_url":"https://github.com/qinyao-he.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Bit-RNN\n\nSource code for paper: [Effective Quantization Methods for Recurrent Neural Networks](https://arxiv.org/abs/1611.10176).\n\nThe implementation of PTB language model is modified from examples in [tensorflow](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/models/rnn/ptb).\n\n## Requirments\n\nCurrently tested and run on [TensorFlow](https://www.tensorflow.org) 1.8 and Python 3.6. View other branches for legacy support.\nYou may download the data from [http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz](http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz).\n\n## Run\n```\npython train.py --config=config.gru --data_path=YOUR_DATA_PATH\n```\n\nCurrently default is 2-bit weights and activations. You may edit the config file in config folder to change configuration.\n\n## Support\nSubmit issue for problem relate to the code itself. Send email to the author for general question about the paper.\n\n## Citation\nPlease cite follow if you use our code in your research:\n```\n@article{DBLP:journals/corr/HeWZWYZZ16,\n  author    = {Qinyao He and\n               He Wen and\n               Shuchang Zhou and\n               Yuxin Wu and\n               Cong Yao and\n               Xinyu Zhou and\n               Yuheng Zou},\n  title     = {Effective Quantization Methods for Recurrent Neural Networks},\n  journal   = {CoRR},\n  volume    = {abs/1611.10176},\n  year      = {2016},\n  url       = {http://arxiv.org/abs/1611.10176},\n  timestamp = {Thu, 01 Dec 2016 19:32:08 +0100},\n  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/HeWZWYZZ16},\n  bibsource = {dblp computer science bibliography, http://dblp.org}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqinyao-he%2Fbit-rnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqinyao-he%2Fbit-rnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqinyao-he%2Fbit-rnn/lists"}