[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-fine-tuning":3},{"tag":4,"articles":10,"peer_article_count":116},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"3725f3eb-5764-4f52-a203-bdfaacae8acc","fine-tuning",4,"微調是把通用模型改造成特定任務工具的關鍵步驟，常見於新詞注入、指令對齊與多模態適配。重點不只在訓練技巧，也在初始化、資料分佈、VRAM 需求與語言覆蓋，直接影響生成品質與部署成本。","Fine-tuning adapts a base model to a narrower task or domain, from seeding new vocabulary and aligning instruction behavior to adapting vision-language models. The practical issues are initialization, data quality, VRAM limits, and language coverage, all of which shape output quality and deployment cost.",[11,20,28,36,44,51,59,66,73,80,87,94,101,108],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"42164bdf-1cae-4f43-ba29-f54d449ae2b9","qvac-turns-consumer-hardware-into-local-ai-en","QVAC turns consumer hardware into local AI","I break down Tether’s QVAC stack and give you a copy-ready pattern for local-first AI on consumer hardware.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781228001859-nhza.png","en","2026-06-12T01:32:54.492313+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"b413d484-6786-4c32-abdc-77f010ac7eba","fine-tuning-beats-rag-style-not-facts-en","Fine-tuning beats RAG when the goal is style, not facts","Fine-tuning is the right tool for teaching an LLM a writing style, while RAG is the wrong tool for that job.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780924681800-5xji.png","2026-06-08T13:17:25.701649+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":33,"image_url":34,"cover_image":34,"language":18,"created_at":35},"d9b6ff74-204d-41d8-a118-669ead54dba0","tether-bitnet-fine-tuning-edge-devices-en","Tether's Bitnet fine-tuning brings AI to edge devices","Tether says its Bitnet LoRA framework can fine-tune a 13B model on consumer devices, pushing AI training closer to phones and PCs.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780729373751-syuq.png","2026-06-06T07:02:26.606426+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":41,"image_url":42,"cover_image":42,"language":18,"created_at":43},"648ed121-8476-4e28-94bb-ab1a4c7b6878","esma-teaches-llms-self-knowledge-en","How ESMA Teaches LLMs Self-Knowledge","A bias-controlled fine-tuning method improves LLM self-knowledge and generalizes across unseen data, languages, and new facts.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780122783226-85qp.png","2026-05-30T06:32:36.492795+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":41,"image_url":49,"cover_image":49,"language":18,"created_at":50},"ec8ce723-21d9-45ee-b847-ae02eeb9b6fa","why-fine-tuning-still-beats-prompt-only-ai-en","Why fine-tuning still beats prompt-only AI","Fine-tuning remains the best way to make foundation models reliable for specific tasks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780120969583-b3ff.png","2026-05-30T06:02:22.115702+00:00",{"id":52,"slug":53,"title":54,"summary":55,"category":56,"image_url":57,"cover_image":57,"language":18,"created_at":58},"6bcb38e2-63e6-4de1-898f-92976aaf003f","5-steps-fine-tune-local-llm-en","5 steps to fine tune a local LLM","5 steps to fine tune a local LLM in a weekend, from setup and data prep to training, evaluation, and GGUF export.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779988670019-xwmt.png","2026-05-28T17:17:23.2414+00:00",{"id":60,"slug":61,"title":62,"summary":63,"category":41,"image_url":64,"cover_image":64,"language":18,"created_at":65},"a3c57be7-a302-4666-a308-113cb75f7494","how-to-build-ai-research-foundations-with-deepmind-en","How to Build AI Research Foundations with DeepMind","Follow this guide to build a practical foundation in modern language models and fine-tuning.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779963500137-2j1d.png","2026-05-28T10:17:24.797504+00:00",{"id":67,"slug":68,"title":69,"summary":70,"category":56,"image_url":71,"cover_image":71,"language":18,"created_at":72},"38035622-f034-46b4-aae9-528b58d6cb94","7-reasons-unsloth-studio-helps-local-ai-en","7 reasons Unsloth Studio helps local AI","7 reasons Unsloth Studio makes local AI training, chat, and export easier with offline workflows and 500+ model support.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779671769367-brbv.png","2026-05-25T01:15:43.542661+00:00",{"id":74,"slug":75,"title":76,"summary":77,"category":16,"image_url":78,"cover_image":78,"language":18,"created_at":79},"3f108c76-04a8-4772-b881-d9eb2a4d7531","21-domain-llms-turn-generic-ai-into-specialists-en","21 domain LLMs turn generic AI into specialists","I break down 21 specialty LLMs and turn that list into a copy-ready playbook for picking, tuning, and shipping one.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779325473556-qv5g.png","2026-05-21T01:03:46.758463+00:00",{"id":81,"slug":82,"title":83,"summary":84,"category":41,"image_url":85,"cover_image":85,"language":18,"created_at":86},"4ed1af1c-05fe-425c-a296-464dbfca0e73","peft-bench-fine-tuning-methods-benchmark-en","PEFT-Bench compares fine-tuning methods fairly","PEFT-Bench standardizes how to compare PEFT methods across 27 NLP datasets and 7 techniques.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779179046277-spz9.png","2026-05-19T08:23:37.63089+00:00",{"id":88,"slug":89,"title":90,"summary":91,"category":41,"image_url":92,"cover_image":92,"language":18,"created_at":93},"18fb2e62-3d41-4b4c-8d65-e91e5f20ea28","microsoft-goalcover-fine-tuning-gaps-en","Microsoft’s GoalCover finds fine-tuning gaps","Microsoft Research’s GoalCover spots missing capabilities in fine-tuning data before training, and improved Qwen-3-14B reward scores.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778462450292-viev.png","2026-05-11T01:20:34.483926+00:00",{"id":95,"slug":96,"title":97,"summary":98,"category":41,"image_url":99,"cover_image":99,"language":18,"created_at":100},"05451495-1e4d-4e70-855f-f92e68a1a699","how-to-build-vintage-llm-testbed-5-steps-en","How to Build a Vintage LLM Testbed in 5 Steps","Build a 1930-cutoff LLM testbed to study historical reasoning and contamination-free generalization.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777945253760-2l44.png","2026-05-05T01:40:33.098256+00:00",{"id":102,"slug":103,"title":104,"summary":105,"category":16,"image_url":106,"cover_image":106,"language":18,"created_at":107},"e031b580-6869-4e89-886d-f190e0adfa86","unsloth-qwen35-partial-fine-tuning-en","Unsloth Adds Part-by-Part Qwen3.5 Fine-Tuning","Unsloth now lets you fine-tune Qwen3.5 vision models by layer type, with faster training, lower VRAM, and 201-language support.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775218020650-71sw.png","2026-04-03T12:06:39.044523+00:00",{"id":109,"slug":110,"title":111,"summary":112,"category":113,"image_url":114,"cover_image":114,"language":18,"created_at":115},"e487e7c6-aa22-484d-9555-46261cc7a91d","grounded-token-initialization-new-vocabulary-en","A Better Way to Seed New LM Tokens","GTI grounds new vocabulary tokens before fine-tuning, aiming to preserve distinctions that mean initialization tends to collapse.","blockchain","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775196588405-1a7u.png","2026-04-03T06:09:29.832749+00:00",9]