{"id":25895921,"url":"https://github.com/mathis-lambert/dockerize-llamacpp","last_synced_at":"2026-03-06T11:31:34.744Z","repository":{"id":184305348,"uuid":"671657370","full_name":"mathis-lambert/dockerize-llamacpp","owner":"mathis-lambert","description":null,"archived":false,"fork":false,"pushed_at":"2023-07-27T20:42:02.000Z","size":2,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-02T22:34:13.313Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"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/mathis-lambert.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}},"created_at":"2023-07-27T20:41:51.000Z","updated_at":"2023-07-27T20:41:51.000Z","dependencies_parsed_at":"2023-07-27T21:51:02.021Z","dependency_job_id":null,"html_url":"https://github.com/mathis-lambert/dockerize-llamacpp","commit_stats":null,"previous_names":["mathis-lambert/dockerize-llamacpp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mathis-lambert/dockerize-llamacpp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mathis-lambert%2Fdockerize-llamacpp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mathis-lambert%2Fdockerize-llamacpp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mathis-lambert%2Fdockerize-llamacpp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mathis-lambert%2Fdockerize-llamacpp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mathis-lambert","download_url":"https://codeload.github.com/mathis-lambert/dockerize-llamacpp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mathis-lambert%2Fdockerize-llamacpp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30173694,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-06T07:56:45.623Z","status":"ssl_error","status_checked_at":"2026-03-06T07:55:55.621Z","response_time":250,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":"2025-03-02T22:34:21.380Z","updated_at":"2026-03-06T11:31:34.723Z","avatar_url":"https://github.com/mathis-lambert.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dockeriser LLama.cpp\n------------------------\n## Prérequis\n- Docker-Engine\n- git\n## Ressources\n- Repo Github : https://github.com/ggerganov/llama.cpp/tree/master\n- Page HF TheBloke : https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML\n\n## Installation\n#### 1. Cloner le repo\n```bash\ngit clone https://github.com/ggerganov/llama.cpp.git llama\n```\n#### 2. Se placer dans le dossier du repo\n```bash\ncd llama\n```\n#### 3. Télécharger le modèle \\{{bit_number}}, \\{{version}}\n```bash\nllama-2-13b-chat.ggmlv3.q{{bit_number}}_{{version}}.bin\n```\nPar exemple pour la version 1.1 du q_4 bits : \n(Pour les autres versions, se réferer à : [Page HF TheBloke](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML))\n```bash\nwget https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/resolve/main/llama-2-13b-chat.ggmlv3.q4_1.bin\n```\n#### 4. Copier le modèle dans le dossier du ./models\n```bash\nmv llama-2-13b-chat.ggmlv3.q{{bit_number}}_{{version}}.bin ./models\n```\n\n## Utilisation\n\n#### 1. Script sh à mettre dans llama.cpp\n```bash\n#!/bin/bash\n./main -ins \\\n-f /llama/prompts/alpaca.txt \\\n-t 8 \\\n-ngl 1 \\\n-m /llama/models/llama-2-13b-chat.ggmlv3.q4_1.bin \\\n--color \\\n--temp 0.7 \\\n--repeat_penalty 1.1 \\\n-s 42 \\\n-n -1\n```\n\n#### 2. Dockerfile (dans llama.cpp)\n```dockerfile\nFROM ubuntu:latest\n\nRUN apt-get update \u0026\u0026 \\\n    apt-get install -y build-essential python3 python3-pip git\n\nCOPY . /llama\n\nWORKDIR /llama\n\n# RUN make\nRUN make clean\nRUN make\nRUN chmod +x run.sh\n\nCMD [\"/llama/run.sh\"]\n```\n\n#### 3. Build de l'image\n```bash\ndocker build -t llama .\n```\n\n#### 4. Lancement du container\n```bash\ndocker run -it llama\n```\n\n#### 5. Lancement du script\nLe script démarrera automatiquement lors du démarrage du container en -it (interactive mode)\n\n## DOCKER avec CUDA\nSe renseigner [en cliquant ICI](https://github.com/ggerganov/llama.cpp/blob/master/README.md#docker-with-cuda)\n- `make LLAMA_CUBLAS=1`\n- `--gpus all`\n- `--n-gpu-layers 1`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmathis-lambert%2Fdockerize-llamacpp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmathis-lambert%2Fdockerize-llamacpp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmathis-lambert%2Fdockerize-llamacpp/lists"}