{"id":29840459,"url":"https://github.com/ibebbs/llm-clasification","last_synced_at":"2026-02-08T05:01:30.427Z","repository":{"id":295381785,"uuid":"636653190","full_name":"ibebbs/LLM-Clasification","owner":"ibebbs","description":null,"archived":false,"fork":false,"pushed_at":"2023-05-05T10:37:24.000Z","size":10,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-29T14:58:21.977Z","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/ibebbs.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,"zenodo":null}},"created_at":"2023-05-05T10:37:14.000Z","updated_at":"2023-05-05T10:37:15.000Z","dependencies_parsed_at":"2025-05-25T08:41:38.012Z","dependency_job_id":"b7b0f076-8d3b-4d9a-836d-69b451b71982","html_url":"https://github.com/ibebbs/LLM-Clasification","commit_stats":null,"previous_names":["ibebbs/llm-clasification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ibebbs/LLM-Clasification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibebbs%2FLLM-Clasification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibebbs%2FLLM-Clasification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibebbs%2FLLM-Clasification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibebbs%2FLLM-Clasification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ibebbs","download_url":"https://codeload.github.com/ibebbs/LLM-Clasification/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ibebbs%2FLLM-Clasification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29221706,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-08T03:18:47.732Z","status":"ssl_error","status_checked_at":"2026-02-08T03:15:31.985Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":"2025-07-29T14:14:33.735Z","updated_at":"2026-02-08T05:01:30.413Z","avatar_url":"https://github.com/ibebbs.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"## Docker\nThis solution is best deployed via Docker using the attached `dockerfile`. Instructions below and for Windows and may need some finessing for other platforms.\n\n### Requirements:\n1. Docker Desktop\n2. A CUDA compatible GPU with \u003e20Gb of VRAM (i.e. an RTX 3080 or above; I use an RTX A4500)\n3. Latest GFX card drives installer\n\n### Build\nFirst build the docker image by running the following command from the repo directory: `docker build -t \u003cusername\u003e/llama-lora-tuner:hackdays .` (replace username with your docker hub user name if you have one, otherwise any other short value)\n\nThis will download and install all the requirements to run `https://github.com/zetavg/LLaMA-LoRA`\n\n### Running\nOnce built, the docker container can be run using: `docker run -it --rm --gpus=all -p 7860:7860 -v ${PWD}/data:/data -v ${PWD}/cache:/LLaMA-LoRA-Tuner/cache -e PYTORCH_TRANSFORMERS_CACHE=/LLaMA-LoRA-Tuner/cache ibebbs/llama-lora-tuner:hackdays` (replace username with your docker hub user name if you have one, otherwise any other short value)\n\nThe first time you run this container, it will download a base model (decapoda/llama-7b) for evaluation/fine tuning to the local `cache` directory (so subsequent runs don't need to download it again). Once downloaded and initialized, a webserver will be started at \"http://0.0.0.0:7860\" which can be loaded in your browser by visiting \"http://localhost:7860\".\n\n### Validating\nOne running, the app should have everything needed to perform inference. Simply enter a prompt (i.e. \"Tell me about Alpacas\") in the \"Instrunction\" box and click the \"Generate\" button. In 40-50 seconds (the first time is slow as it prepares the model for inference, subsequent calls should be much faster) you should see some text generated in the \"Output\" box.\n\n### Restarting\nNow everything is downloaded, you should be able to quickly restart the docker container without needing to re-download the model by using the same command above.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fibebbs%2Fllm-clasification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fibebbs%2Fllm-clasification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fibebbs%2Fllm-clasification/lists"}