{"id":18885547,"url":"https://github.com/togethercomputer/quick_deployment_helm","last_synced_at":"2025-04-14T21:30:58.180Z","repository":{"id":97015338,"uuid":"585925307","full_name":"togethercomputer/Quick_Deployment_HELM","owner":"togethercomputer","description":null,"archived":false,"fork":false,"pushed_at":"2023-10-02T23:52:07.000Z","size":345,"stargazers_count":7,"open_issues_count":6,"forks_count":8,"subscribers_count":2,"default_branch":"main","last_synced_at":"2023-10-03T08:03:59.767Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/togethercomputer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"licenses.csv","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-01-06T13:12:19.000Z","updated_at":"2023-07-25T15:06:05.000Z","dependencies_parsed_at":"2023-10-03T04:55:04.603Z","dependency_job_id":"92380e31-9253-4fe7-8559-1a4f096d6b90","html_url":"https://github.com/togethercomputer/Quick_Deployment_HELM","commit_stats":null,"previous_names":[],"tags_count":111,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FQuick_Deployment_HELM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FQuick_Deployment_HELM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FQuick_Deployment_HELM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/togethercomputer%2FQuick_Deployment_HELM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/togethercomputer","download_url":"https://codeload.github.com/togethercomputer/Quick_Deployment_HELM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223645365,"owners_count":17178916,"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":[],"created_at":"2024-11-08T07:19:43.608Z","updated_at":"2024-11-08T07:19:44.383Z","avatar_url":"https://github.com/togethercomputer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Quick_Deployment_HELM\n\nTo deploy a new docker image, merge a PR to the main branch.\n\n### To bring up a local REST server:\n\n```console\nmkdir -p .together/models\nchmod 777 .together .together/models\ndocker run --rm --gpus device=0 \\\n  -v $PWD/.together:/home/user/.together \\\n  -e HF_HOME=/home/user/.together/models \\\n  -e HTTP_HOST=0.0.0.0 \\\n  -e SERVICE_DOMAIN=http \\\n  -p 5001:5001 \\\n  -it togethercomputer/native_hf_models /usr/bin/python3 serving_local_nlp_model.py --hf_model_name facebook/opt-350m\n```\n\n```console\ncurl -X POST -H 'Content-Type: application/json' http://localhost:5001/ -d '{\"prompt\": \"Space robots\"}'\n```\n\n```console\n{\"result_type\": \"language-model-inference\", \"choices\": [{\"text\": \" are a great way to get a lot of work done.\", \"index\": 0, \"finish_reason\": \"length\"}], \"raw_compute_time\": 0.20327712898142636}\n```\n\n### Bridge local REST server to Together Inference API:\n\n```console\ntogether-node start -f none --worker.mode existing-service --worker.service my-foobar --worker.port 5001\n```\n\n```console\ncurl -X POST https://api.together.xyz/inference \\\n  -H 'Content-Type: application/json' \\\n  -H 'Authorization: Bearer YOUR-API-KEY-HERE' \\\n  -d '{\n  \"model\": \"my-foobar\",\n  \"prompt\": \"Space robots\"\n}'\n```\n\n```console\n{\"status\":\"finished\",\"prompt\":[\"Space robots\"],\"model\":\"my-foobar\",\"model_owner\":\"\",\"tags\":{},\"num_returns\":1,\"args\":{\"model\":\"my-foobar\",\"prompt\":\"Space robots\"},\"subjobs\":[],\"output\":{\"choices\":[{\"finish_reason\":\"length\",\"index\":0,\"text\":\" are a great way to get a lot of work done.\"}],\"raw_compute_time\":0.20714728604070842,\"result_type\":\"language-model-inference\"}}\n```\n\n### To bring up a standalone node:\n\n```console\ndocker run --pull=always --rm --gpus device=2 \\\n -v $PWD/.together:/home/user/.together \\\n -it togethercomputer/native_hf_models /usr/local/bin/together-node start \\\n --config /home/user/cfg-neoxt.yaml --color \\\n --worker.service OpenChatTest --worker.model gpt-neoxt-v0.15\n```\n\n### To bring up a standalone node with retrieval:\n\n```console\ndocker run --pull=always --rm --gpus device=2 \\\n --add-host=host.docker.internal:host-gateway \\\n -v $PWD/.together:/home/user/.together \\\n -it togethercomputer/native_hf_models /usr/local/bin/together-node start \\\n --config /home/user/cfg-neoxt-retrieval.yaml --color \\\n --worker.service ock-faiss --worker.model gpt-neoxt-v0.15\n```\n\n### To bring up a standalone safety model:\n\n```console\ndocker run --pull=always --rm --gpus device=2 \\\n -v $PWD/.together:/home/user/.together \\\n -it togethercomputer/native_hf_models /usr/local/bin/together-node start \\\n --config /home/user/cfg-neoxt.yaml --color \\\n --worker.service SafetyTest --worker.model gpt-jt-safety\n```\n\n### Start opt-350m in CPU on Mac laptop:\n\n```console\n~/together-node/build/together-node start --config ./cfg-opt-350m-docker-macos.yaml\n```\n\n### Start opt-350m in CPU on Linux:\n\n```console\ncurl -O https://together-distro-packages.s3.us-west-2.amazonaws.com/linux/x86_64/bin/together-node-latest\nchmod a+x ./together-node-latest\n./together-node-latest start --config ./cfg-opt-350m-docker.yaml\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftogethercomputer%2Fquick_deployment_helm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftogethercomputer%2Fquick_deployment_helm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftogethercomputer%2Fquick_deployment_helm/lists"}