{"data":{"slug":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","stars_delta_30d":-2,"url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","description":"Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.","homepage_url":null,"license":"Apache-2.0","open_issues":16,"watchers":16,"ai_summary":"A comprehensive toolkit to facilitate the fine-tuning, ablation studies, and unit-testing of various open-source LLMs.","readme_excerpt":"## Quick Start\n\nThis guide contains 3 stages that will enable you to get the most out of this toolkit!\n\n- **Basic**: Run your first LLM fine-tuning experiment\n- **Intermediate**: Run a custom experiment by changing the components of the YAML configuration file\n- **Advanced**: Launch series of fine-tuning experiments across different prompt templates, LLMs, optimization techniques -- all through **one** YAML configuration file","github_created_at":"2023-07-24T14:22:42+00:00","created_at":"2026-07-11T11:39:47.949751+00:00","updated_at":"2026-08-24T06:01:02.432153+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ablation-study","name":"ablation-study"},{"slug":"classification","name":"classification"},{"slug":"falcon","name":"falcon"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"flan-t5","name":"flan-t5"},{"slug":"large-language-models","name":"large language models"},{"slug":"llama2","name":"llama2"},{"slug":"lora","name":"lora"}],"trust":{"provenance":{"is_fork":false,"github_id":670206497,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-24T06:01:01.633Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":111,"last_release_at":"2024-07-25T15:15:43Z","stars_delta_30d":-2,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:39:49.492Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-24T06:01:02.100Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-24T06:01:02.100Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-24T06:01:02.100Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-24T06:01:02.100Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-24T06:01:02.100Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-24T06:01:02.100Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When working specifically with Falcon, Flan-T5, LLama2, Mistral-7B or Zephyr models due to inbuilt support","For researchers needing a framework that supports both fine-tuning and unit-testing in a single package"],"when_not_to_use":["If prioritizing proprietary LLMs not listed as supported within the toolkit","When working with languages other than Python, since toolkit is exclusively for Python environments"],"source":"enrich:decision_facts","observed_at":"2026-07-14T18:55:19.521Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Facilitates fine-tuning of open-source LLMs with features for ablation studies and unit testing"}]}}