Mastodon

LLMsFine tuning или RAG. Что выбрать? 🐝 RAG vs Fine tuning. В чём разница?... <a href="https://habr.com/ru/articles/898026/?utm_source=habrahabr&utm_medium=rss&utm_campaign=898026" rel="nofollow noopener noreferrer" target="_blank">https://habr.com/ru/articles/898026/?utm_source=habrahabr&utm_medium=rss&utm_campaign=898026</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/typescript" target="_blank">#typescript</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/javascript" target="_blank">#javascript</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/python" target="_blank">#python</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/rag" target="_blank">#rag</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/ml" target="_blank">#ml</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/yandex.cloud" target="_blank">#yandex.cloud</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/машинное+обучение" target="_blank">#машинное+обучение</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/исскуственный" target="_blank">#исскуственный</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/интеллект" target="_blank">#интеллект</a> <a href="https://awakari.com/pub-msg.html?id=0JLgz163e2c1jrZ1vTwkep9rZWi" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

HabrFine tuning или RAG. Что выбрать?🐝 RAG vs Fine tuning. В чём разница? При разработке ИИ проектов существует два способа интеграции внешних данных: RAG хранилища и Fine tuning. Для не технаря отличия не очевидны. Я сделал short summary, чтобы по существу изложить плюсы и минусы двух решений<a href="https://habr.com/ru/articles/898026/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/articles/898026/</a><a href="https://zhub.link/tags/typescript" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#typescript</a> <a href="https://zhub.link/tags/javascript" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#javascript</a> <a href="https://zhub.link/tags/python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#python</a> <a href="https://zhub.link/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a href="https://zhub.link/tags/rag" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#rag</a> <a href="https://zhub.link/tags/ml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ml</a> <a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://zhub.link/tags/yandexcloud" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#yandexcloud</a> <a href="https://zhub.link/tags/%D0%BC%D0%B0%D1%88%D0%B8%D0%BD%D0%BD%D0%BE%D0%B5" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#машинное</a>+обучение <a href="https://zhub.link/tags/%D0%B8%D1%81%D1%81%D0%BA%D1%83%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D1%8B%D0%B9_%D0%B8%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#исскуственный_интеллект</a>

Python-Job-AlertFine tuning роя агентов 🐝 Fine tuning роя агентов В вакансиях LL... <a href="https://habr.com/ru/articles/897674/?utm_source=habrahabr&utm_medium=rss&utm_campaign=897674" rel="nofollow noopener noreferrer" target="_blank">https://habr.com/ru/articles/897674/?utm_source=habrahabr&utm_medium=rss&utm_campaign=897674</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/typescript" target="_blank">#typescript</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/javascript" target="_blank">#javascript</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/python" target="_blank">#python</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/dataset" target="_blank">#dataset</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/huggingface" target="_blank">#huggingface</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/yandexgpt" target="_blank">#yandexgpt</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/openai" target="_blank">#openai</a> <a href="https://awakari.com/pub-msg.html?id=Co4ot0ze4quwnIMCoUesqYhhUcy" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

LLMsFine tuning роя агентов 🐝 Fine tuning роя агентов В вакансиях LL... <a href="https://habr.com/ru/articles/897674/?utm_source=habrahabr&utm_medium=rss&utm_campaign=897674" rel="nofollow noopener noreferrer" target="_blank">https://habr.com/ru/articles/897674/?utm_source=habrahabr&utm_medium=rss&utm_campaign=897674</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/typescript" target="_blank">#typescript</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/javascript" target="_blank">#javascript</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/python" target="_blank">#python</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/dataset" target="_blank">#dataset</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/huggingface" target="_blank">#huggingface</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/yandexgpt" target="_blank">#yandexgpt</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/openai" target="_blank">#openai</a> <a href="https://awakari.com/pub-msg.html?id=X79MVUmRR5ZBKeLX4jSgqQGobY0" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

HabrFine tuning роя агентов🐝 Fine tuning роя агентов В вакансиях LLM инженеров присутствует слово RAG. Это подразумевает интеграцию во внешнюю базу данных. Можно дешевле - fine tuning . Что это и как поставить работу описано в этой статье<a href="https://habr.com/ru/articles/897674/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/articles/897674/</a><a href="https://zhub.link/tags/typescript" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#typescript</a> <a href="https://zhub.link/tags/javascript" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#javascript</a> <a href="https://zhub.link/tags/python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#python</a> <a href="https://zhub.link/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a href="https://zhub.link/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#machinelearning</a> <a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://zhub.link/tags/dataset" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#dataset</a> <a href="https://zhub.link/tags/huggingface" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#huggingface</a> <a href="https://zhub.link/tags/yandexgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#yandexgpt</a> <a href="https://zhub.link/tags/openai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#openai</a>

HabrZero-shot и Few-shot Learning в NLPZero-shot Learning (ZSL) - это способность модели выполнять задачи без каких-либо примеров обучения. Она делает это за счёт обобщённых знаний, полученных во время предобучения. Few-shot Learning (FSL) - это метод, при котором модели предоставляется всего несколько примеров (обычно от 1 до 5), чтобы лучше понять структуру задачи.<a href="https://habr.com/ru/articles/897604/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/articles/897604/</a><a href="https://zhub.link/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#NLP</a> <a href="https://zhub.link/tags/Zeroshot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Zeroshot</a> <a href="https://zhub.link/tags/Fewshot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Fewshot</a> <a href="https://zhub.link/tags/Finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Finetuning</a> <a href="https://zhub.link/tags/Zeroshot_%D0%B8_Fewshot_Learning_%D0%B2_NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Zeroshot_и_Fewshot_Learning_в_NLP</a> <a href="https://zhub.link/tags/Zeroshot_%D0%B8%D0%BB%D0%B8_Fewshot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Zeroshot_или_Fewshot</a>

Alvin AshcraftAI Toolkit for VS Code March Update. <a href="https://buff.ly/pwcxAW9" rel="nofollow noopener noreferrer" target="_blank">buff.ly/pwcxAW9</a> <a class="hashtag" href="https://bsky.app/search?q=%23ai" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a class="hashtag" href="https://bsky.app/search?q=%23vscode" rel="nofollow noopener noreferrer" target="_blank">#vscode</a> <a class="hashtag" href="https://bsky.app/search?q=%23aitoolkit" rel="nofollow noopener noreferrer" target="_blank">#aitoolkit</a> <a class="hashtag" href="https://bsky.app/search?q=%23aimodels" rel="nofollow noopener noreferrer" target="_blank">#aimodels</a> <a class="hashtag" href="https://bsky.app/search?q=%23prompting" rel="nofollow noopener noreferrer" target="_blank">#prompting</a> <a class="hashtag" href="https://bsky.app/search?q=%23finetuning" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a href="https://buff.ly/pwcxAW9" rel="nofollow noopener noreferrer" target="_blank">AI Toolkit for VS Code March U...</a>

Alvin Ashcraft 🐿️AI Toolkit for VS Code March Update.<a href="https://techcommunity.microsoft.com/blog/azuredevcommunityblog/ai-toolkit-for-vs-code-march-update/4396880" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://techcommunity.microsoft.com/blog/azuredevcommunityblog/ai-toolkit-for-vs-code-march-update/4396880</a><a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://hachyderm.io/tags/vscode" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#vscode</a> <a href="https://hachyderm.io/tags/aitoolkit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#aitoolkit</a> <a href="https://hachyderm.io/tags/aimodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#aimodels</a> <a href="https://hachyderm.io/tags/prompting" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#prompting</a> <a href="https://hachyderm.io/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a>

Nicole HennigResearchers warn of ‘catastrophic overtraining’ in LLMs <a href="https://venturebeat.com/ai/researchers-warn-of-catastrophic-overtraining-in-large-language-models/" rel="nofollow noopener noreferrer" target="_blank">https://venturebeat.com/ai/researchers-warn-of-catastrophic-overtraining-in-large-language-models/</a> <a class="hashtag" href="https://bsky.app/search?q=%23AI" rel="nofollow noopener noreferrer" target="_blank">#AI</a> <a class="hashtag" href="https://bsky.app/search?q=%23FineTuning" rel="nofollow noopener noreferrer" target="_blank">#FineTuning</a> <a class="hashtag" href="https://bsky.app/search?q=%23TradeOffs" rel="nofollow noopener noreferrer" target="_blank">#TradeOffs</a>

Nicole HennigResearchers warn of ‘catastrophic overtraining’ in LLMs <a href="https://venturebeat.com/ai/researchers-warn-of-catastrophic-overtraining-in-large-language-models/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://venturebeat.com/ai/researchers-warn-of-catastrophic-overtraining-in-large-language-models/</a> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#AI</a> <a href="https://techhub.social/tags/FineTuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#FineTuning</a> <a href="https://techhub.social/tags/TradeOffs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#TradeOffs</a>

LLMsRAG vs. Fine-Tuning: Strategic Choices for Enterprise AI Systems The biggest headache for enterpr... <a href="https://medium.com/@wmechem/rag-vs-fine-tuning-strategic-choices-for-enterprise-ai-systems-fc9f3bcb65ff?source=rss------machine_learning-5" rel="nofollow noopener noreferrer" target="_blank">https://medium.com/@wmechem/rag-vs-fine-tuning-strategic-choices-for-enterprise-ai-systems-fc9f3bcb65ff?source=rss------machine_learning-5</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/ai" target="_blank">#ai</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/rags" target="_blank">#rags</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a href="https://awakari.com/pub-msg.html?id=8ppmTT0TmJ1geeoIUJY746rkMbI" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

Alvin AshcraftAI Toolkit for Visual Studio Code Now Supports NVIDIA NIM Microservices for RTX AI PCs. <a href="https://buff.ly/3AjxM1I" rel="nofollow noopener noreferrer" target="_blank">buff.ly/3AjxM1I</a> <a class="hashtag" href="https://bsky.app/search?q=%23vscode" rel="nofollow noopener noreferrer" target="_blank">#vscode</a> <a class="hashtag" href="https://bsky.app/search?q=%23ai" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a class="hashtag" href="https://bsky.app/search?q=%23aitoolkit" rel="nofollow noopener noreferrer" target="_blank">#aitoolkit</a> <a class="hashtag" href="https://bsky.app/search?q=%23finetuning" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a class="hashtag" href="https://bsky.app/search?q=%23aimodels" rel="nofollow noopener noreferrer" target="_blank">#aimodels</a> <a class="hashtag" href="https://bsky.app/search?q=%23modelcatalog" rel="nofollow noopener noreferrer" target="_blank">#modelcatalog</a> <a class="hashtag" href="https://bsky.app/search?q=%23nvidia" rel="nofollow noopener noreferrer" target="_blank">#nvidia</a> <a href="https://buff.ly/3AjxM1I" rel="nofollow noopener noreferrer" target="_blank">AI Toolkit for Visual Studio C...</a>

Alvin Ashcraft 🐿️AI Toolkit for Visual Studio Code Now Supports NVIDIA NIM Microservices for RTX AI PCs.<a href="https://techcommunity.microsoft.com/blog/azuredevcommunityblog/ai-toolkit-for-visual-studio-code-now-supports-nvidia-nim-microservices-for-rtx-/4396736" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://techcommunity.microsoft.com/blog/azuredevcommunityblog/ai-toolkit-for-visual-studio-code-now-supports-nvidia-nim-microservices-for-rtx-/4396736</a><a href="https://hachyderm.io/tags/vscode" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#vscode</a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://hachyderm.io/tags/aitoolkit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#aitoolkit</a> <a href="https://hachyderm.io/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a href="https://hachyderm.io/tags/aimodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#aimodels</a> <a href="https://hachyderm.io/tags/modelcatalog" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#modelcatalog</a> <a href="https://hachyderm.io/tags/nvidia" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#nvidia</a>

LLMsFine-Tuning a Finance Advisor with QLoRA for Smarter Financial Recommendations Introduction Conti... <a href="https://medium.com/@mark.mazur007/fine-tuning-a-finance-advisor-with-qlora-for-smarter-financial-recommendations-47366d229547?source=rss------machine_learning-5" rel="nofollow noopener noreferrer" target="_blank">https://medium.com/@mark.mazur007/fine-tuning-a-finance-advisor-with-qlora-for-smarter-financial-recommendations-47366d229547?source=rss------machine_learning-5</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/qlora" target="_blank">#qlora</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/deep-learning" target="_blank">#deep-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a href="https://awakari.com/pub-msg.html?id=DW8BXtWw8JgMYl7elwYQNOW8Lk8" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

LLMsTitle: Fine-Tuning Large Language Models: A Deep Dive into LLaMA & DeepSeek-Math Introduction... <a href="https://medium.com/@Uzair_Qaiser/title-fine-tuning-large-language-models-a-deep-dive-into-llama-deepseek-math-787691ce51c8?source=rss------machine_learning-5" rel="nofollow noopener noreferrer" target="_blank">https://medium.com/@Uzair_Qaiser/title-fine-tuning-large-language-models-a-deep-dive-into-llama-deepseek-math-787691ce51c8?source=rss------machine_learning-5</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llama-3" target="_blank">#llama-3</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/ai" target="_blank">#ai</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/deepseek" target="_blank">#deepseek</a> <a href="https://awakari.com/pub-msg.html?id=5Ltum1WrAC6u3Zd4KfT6ekwbxI0" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

LLMsFine-Tuning Large Language Models: A Deep Dive into LLaMA & DeepSeek-Math Introduction Contin... <a href="https://medium.com/@mirzasarim2888/fine-tuning-large-language-models-a-deep-dive-into-llama-deepseek-math-4e8c2f6ada24?source=rss------machine_learning-5" rel="nofollow noopener noreferrer" target="_blank">https://medium.com/@mirzasarim2888/fine-tuning-large-language-models-a-deep-dive-into-llama-deepseek-math-4e8c2f6ada24?source=rss------machine_learning-5</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/nlp" target="_blank">#nlp</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llama-2" target="_blank">#llama-2</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/ai" target="_blank">#ai</a> <a href="https://awakari.com/pub-msg.html?id=E2JcGMArjEDwG57dQWwyjxWhdaa" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

Sarah LeaShould your LLM memorize everything or just look it up? Let’s break it down.<a href="https://towardsdatascience.com/how-to-make-your-llm-more-accurate-with-rag-fine-tuning/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://towardsdatascience.com/how-to-make-your-llm-more-accurate-with-rag-fine-tuning/</a><a href="https://techhub.social/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://techhub.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://techhub.social/tags/rag" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#rag</a> <a href="https://techhub.social/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a href="https://techhub.social/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#chatgpt</a> <a href="https://techhub.social/tags/openai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#openai</a> <a href="https://techhub.social/tags/deepseek" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#deepseek</a> <a href="https://techhub.social/tags/deeplearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#deeplearning</a> <a href="https://techhub.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#machinelearning</a> <a href="https://techhub.social/tags/technology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#technology</a>

LLMsFine-Tuning 101: Unlocking the Power of AI Customization Learn fine-tuning comprehensively and bu... <a href="https://medium.com/@dhruvdtiwari/fine-tuning-101-unlocking-the-power-of-ai-customization-8bf46b667297?source=rss------machine_learning-5" rel="nofollow noopener noreferrer" target="_blank">https://medium.com/@dhruvdtiwari/fine-tuning-101-unlocking-the-power-of-ai-customization-8bf46b667297?source=rss------machine_learning-5</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/ai" target="_blank">#ai</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a href="https://awakari.com/pub-msg.html?id=ZQhJLCXCbnZOy1Cl9hk26O4ermC" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

Habr[Перевод] Оценка больших языковых моделей в 2025 году: пять методовБольшие языковые модели (LLM) в последнее время стремительно развиваются и несут в себе потенциал для кардинального преобразования ИИ. Точная оценка моделей LLM крайне важна, поскольку: • Компании должны выбирать генеративные AI-модели для внедрения в работу. Базовых моделей LLM сейчас множество, и для каждой есть различные их модификации. • После выбора модели будет проходить fine-tuning. И если производительность модели не измерена с достаточной точностью, пользователи не смогут оценить эффективность своих усилий. Таким образом, необходимо определить: • Оптимальные методы оценки моделей • Подходящий тип данных для обучения и тестирования моделей Поскольку оценка систем LLM является многомерной задачей, важно разработать комплексную методологию измерения их производительности. В этой статье рассматриваются основные проблемы существующих методов оценки и предлагаются решения для их устранения.<a href="https://habr.com/ru/articles/887290/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/articles/887290/</a><a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://zhub.link/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://zhub.link/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#benchmarking</a> <a href="https://zhub.link/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#finetuning</a> <a href="https://zhub.link/tags/bleu" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#bleu</a> <a href="https://zhub.link/tags/rouge" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#rouge</a> <a href="https://zhub.link/tags/%D0%B1%D0%B5%D0%BD%D1%87%D0%BC%D0%B0%D1%80%D0%BA%D0%B8%D0%BD%D0%B3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#бенчмаркинг</a>

LLMsUniversal Fine-Tuning Framework (UFTF): A Versatile and Efficient Approach to Fine-Tuning Languag... <a href="https://medium.com/ai-simplified-in-plain-english/universal-fine-tuning-framework-uftf-a-versatile-and-efficient-approach-to-fine-tuning-language-91c6238bcacc?source=rss------machine_learning-5" rel="nofollow noopener noreferrer" target="_blank">https://medium.com/ai-simplified-in-plain-english/universal-fine-tuning-framework-uftf-a-versatile-and-efficient-approach-to-fine-tuning-language-91c6238bcacc?source=rss------machine_learning-5</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/machine-learning" target="_blank">#machine-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/open-source" target="_blank">#open-source</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/fine-tuning" target="_blank">#fine-tuning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/deep-learning" target="_blank">#deep-learning</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a href="https://awakari.com/pub-msg.html?id=Grhks7gVqvqFzDdhFt2swJEYVEm" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>

Recent searches

Search options

Administered by:

Server stats:

#finetuning