{"id":19288535,"url":"https://github.com/samber/go-gpt-3-encoder","last_synced_at":"2025-04-05T03:09:27.846Z","repository":{"id":65196289,"uuid":"580964308","full_name":"samber/go-gpt-3-encoder","owner":"samber","description":"Go BPE tokenizer (Encoder+Decoder) for GPT2 and GPT3","archived":false,"fork":false,"pushed_at":"2024-12-02T07:56:39.000Z","size":571,"stargazers_count":80,"open_issues_count":1,"forks_count":21,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-29T02:05:51.751Z","etag":null,"topics":["bpe","byte-pair-encoding","codex","decoder","encoder","go","gpt-2","gpt-3","openai","token","tokenizer","transformer"],"latest_commit_sha":null,"homepage":"https://pkg.go.dev/github.com/samber/go-gpt-3-encoder","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/samber.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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},"funding":{"github":["samber"]}},"created_at":"2022-12-21T22:53:13.000Z","updated_at":"2025-02-11T15:46:43.000Z","dependencies_parsed_at":"2023-01-11T23:00:50.069Z","dependency_job_id":"97be7a86-5c41-4ba3-b295-3e6e90fc2331","html_url":"https://github.com/samber/go-gpt-3-encoder","commit_stats":{"total_commits":6,"total_committers":4,"mean_commits":1.5,"dds":0.5,"last_synced_commit":"d52dd07fd25f18fb63e8a2406c658286d9e30f70"},"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samber%2Fgo-gpt-3-encoder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samber%2Fgo-gpt-3-encoder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samber%2Fgo-gpt-3-encoder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/samber%2Fgo-gpt-3-encoder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/samber","download_url":"https://codeload.github.com/samber/go-gpt-3-encoder/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247280272,"owners_count":20912967,"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","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":["bpe","byte-pair-encoding","codex","decoder","encoder","go","gpt-2","gpt-3","openai","token","tokenizer","transformer"],"created_at":"2024-11-09T22:09:19.983Z","updated_at":"2025-04-05T03:09:27.822Z","avatar_url":"https://github.com/samber.png","language":"Go","funding_links":["https://github.com/sponsors/samber"],"categories":[],"sub_categories":[],"readme":"# go-gpt-3-encoder\n\nGo BPE tokenizer (Encoder+Decoder) for GPT2 and GPT3.\n\n## About\n\nGPT2 and GPT3 use byte pair encoding to turn text into a series of integers to feed into the model. This is a Go implementation of OpenAI's original Python encoder/decoder which can be found [here](https://github.com/openai/gpt-2/blob/master/src/encoder.py).\n\nThis code was inspired by [Javascript implementation](https://github.com/latitudegames/GPT-3-Encoder) and partially generated by OpenAI himself!\n\n\u003e [!WARNING]\n\u003e This implementation of BPE tokenizer is not valid. See [https://x.com/burkov/status/1863007688470241336](https://x.com/burkov/status/1863007688470241336).\n\n## Install\n\n```bash\ngo get github.com/samber/go-gpt-3-encoder\n```\n\n## Usage\n\n```go\nimport tokenizer \"github.com/samber/go-gpt-3-encoder\"\n\nencoder, err := tokenizer.NewEncoder()\nif err != nil {\n    log.Fatal(err)\n}\n\nstr := \"This is an example sentence to try encoding out on!\"\n\nencoded, err := encoder.Encode(str)\nif err != nil {\n    log.Fatal(err)\n}\n\nfmt.Println(\"We can look at each token and what it represents:\")\nfor _, token := range encoded {\n    fmt.Printf(\"%d -- %s\\n\", token, encoder.Decode([]int{token}))\n}\n\ndecoded := encoder.Decode(encoded)\nfmt.Printf(\"We can decode it back into: %s\\n\", decoded)\n```\n\n## Contribute\n\nSome corner cases are not covered by this library. See `@TODO` in tests.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamber%2Fgo-gpt-3-encoder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsamber%2Fgo-gpt-3-encoder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamber%2Fgo-gpt-3-encoder/lists"}