{"id":24912852,"url":"https://github.com/raynardj/seqtwoseq","last_synced_at":"2025-08-21T00:14:10.616Z","repository":{"id":97434841,"uuid":"134724418","full_name":"raynardj/seqtwoseq","owner":"raynardj","description":"Ray's s2s","archived":false,"fork":false,"pushed_at":"2018-06-22T07:39:03.000Z","size":25,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-03-28T04:37:28.744Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/raynardj.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2018-05-24T14:08:38.000Z","updated_at":"2018-06-22T07:39:04.000Z","dependencies_parsed_at":"2023-03-13T16:13:54.030Z","dependency_job_id":null,"html_url":"https://github.com/raynardj/seqtwoseq","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/raynardj/seqtwoseq","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raynardj%2Fseqtwoseq","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raynardj%2Fseqtwoseq/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raynardj%2Fseqtwoseq/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raynardj%2Fseqtwoseq/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/raynardj","download_url":"https://codeload.github.com/raynardj/seqtwoseq/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raynardj%2Fseqtwoseq/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271406145,"owners_count":24753926,"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":"2025-08-20T02:00:09.606Z","response_time":69,"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":[],"created_at":"2025-02-02T05:28:44.976Z","updated_at":"2025-08-21T00:14:10.611Z","avatar_url":"https://github.com/raynardj.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# seqtwoseq\n\nExperiment on sequence to sequence, for chatbot\n\nSupport both GPU and CPU training.\n\n### Files\n\nThe [model file](models.py) contains the encoder/decoder code\n\nTrain the model using [this notebook](seq2seq_chat.ipynb)\n\nWhile training , you can have [this inference notebook](inference.ipynb) to check the model performance, loading the most recent weights the training notebook has saved.\n\n[Constants file](constants.py) contains the configurations.\n\n### Definitions\n\n#### VERSION\n\nVersion between the model are controlled in following ways:\n```python\nVERSION = \"0.0.3\"\n# \"0.0.1\" chars hidden =256\n# \"0.0.2\" token hidden =512\n# \"0.0.3\" layer=2 hidden =512\n```\nPlease notice, even if you decide to move on the version number, don't delete it, comment it out and write some notes about it for further reference\n\nThe version number will be buried into model weights' file name.\n\n#### CUDA\n\nTrue or False, to the question: are we using the GPU\n\n#### s2s_data\n\n```class s2s_data``` is the dataset class (pytorch dataset class, the kind of class providing neat array data)。\n\nIt's universal to many datasets, all we have to do is to define a load function, pass as arg:load_io\n\nIn notebook, I defined 2 load functions, one for reading data as cn char, the other for tokenized cn words. The all return full_list_of_questions, full_list_of_answers.\n\n* kwarg:build_seq \n\nThe already built sequence(2 lists of sentences) can be saved to npy file. if kwarg:build_seq == False, we don't rebuild sequence again, just load the npy instead.\n\n* kwarg:build_vocab\n\nThe already built/sorted vocabulary can bse saved to csv, if kwarg:build_vocab == False, we don't rebuild vocab again.\n\n### Training\n\nFor detailed information, you'll find my seq2seq_chat.ipynb notebook very informative.\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraynardj%2Fseqtwoseq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fraynardj%2Fseqtwoseq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraynardj%2Fseqtwoseq/lists"}