{"data":{"slug":"hit-scir-huozi","name":"huozi","tagline":"General-purpose large model for fine-tuning and applications","github_url":"https://github.com/HIT-SCIR/huozi","owner":"HIT-SCIR","repo":"huozi","owner_avatar_url":"https://avatars.githubusercontent.com/u/823252?v=4","primary_language":"Python","stars":393,"forks":26,"topics":["fine-tuning","large-language-models","llm","nlp"],"archived":false,"github_pushed_at":"2024-09-12T06:03:40+00:00","maintenance_label":"Dormant","stars_delta_30d":-2,"url":"https://www.graphcanon.com/tools/hit-scir-huozi","markdown_url":"https://www.graphcanon.com/tools/hit-scir-huozi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hit-scir-huozi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hit-scir-huozi","description":"活字通用大模型","homepage_url":null,"license":"Apache-2.0","open_issues":0,"watchers":10,"ai_summary":"Huozi is designed to facilitate the development of large language models for natural language processing tasks through fine-tuning capabilities.","readme_excerpt":"### Quick Start\n\n活字3.5采用ChatML格式的prompt模板，格式为：\n```\n<|beginofutterance|>系统\n{system prompt}<|endofutterance|>\n<|beginofutterance|>用户\n{input}<|endofutterance|>\n<|beginofutterance|>助手\n{output}<|endofutterance|>\n```\n\n使用活字3.5进行推理的示例代码如下：\n```python","github_created_at":"2023-07-30T05:57:52+00:00","created_at":"2026-07-11T11:41:52.660687+00:00","updated_at":"2026-09-20T06:32:01.881316+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":"fine-tuning","name":"fine-tuning"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"llm","name":"llm"},{"slug":"nlp","name":"nlp"}],"trust":{"provenance":{"is_fork":false,"github_id":672449777,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-19T18:28:30.057Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":737,"last_release_at":"2024-09-12T05:41:33Z","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":"2026-07-11T11:41:54.143Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-19T18:28:31.352Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-19T18:28:31.352Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-19T18:28:31.352Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When working on projects that require fast integration of pre-trained language models through its streamlined fine-tuning capabilities.","For developers aiming to enhance specific natural language processing tasks where customization is key."],"when_not_to_use":["If your project requires proprietary licensing, as Huozi is under the Apache-2.0 license which may not meet all business models' requirements.","When needing a framework with comprehensive support for visual data or other non-textual machine learning applications."],"source":"enrich:decision_facts","observed_at":"2026-07-14T21:01:07.664Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Huozi is a Python-based large model framework with Apache-2.0 license for fine-tuning and NLP applications."}]}}