5 Free AI Repos: The Code Is Free, Running It Isn't
Five free AI repos: the code is free, running it isn't. Here's the real bill for each, compute, services and licence (figures at time of filming, checked 23 Oct 2026). Not a dunk: all five are genuinely useful, just check the needs and the licence first.
MiniMind (Apache-2.0): its headline is a tiny ~64M-parameter language model in about 2 hours on a single NVIDIA RTX 3090 (the README's footnote: 2 hours is one epoch of the SFT stage) for about RMB 3 of server cost. Free code, but you need (or rent) a GPU.
OpenClaude: its LICENSE says the repo contains code derived from the proprietary Claude Code CLI; the community changes are MIT only "where legally permissible", and GitHub shows the licence as NOASSERTION. Read the licence before you build on it.
OpenMAIC (MIT): the server needs a PostgreSQL database (DATABASE_URL) plus an AI model provider. Cloud models need an API key (billed by the provider); a local model through Ollama doesn't.
Academic Research Skills (CC BY-NC 4.0, non-commercial): runs inside paid Claude Code with API keys; the author estimates about US$3–7 per 15,000-word paper, and in their own test 21 of 68 references had problems, so check every citation.
Invidious (AGPL-3.0): an alternative YouTube front end; its docs list just five public clearnet instances, so you may end up self-hosting a server.
Which one is worth the hassle?
Sources (all public, no need to comment for them):
MiniMind: jingyaogong/minimind
OpenClaude: Twigpine/openclaude
OpenMAIC: THU-MAIC/OpenMAIC
OpenMAIC setup docs: open.maic.chat
Academic Research Skills: Imbad0202/academic-research-skills
Invidious: iv-org/invidious
Invidious public instances: docs.invidious.io
#AI #OpenSource #GitHub #shorts
Made with AI-generated visuals and voice.
1 like · 135 views
想自己搞个 AI 小玩具玩玩，还能顺便研究一下大模型到底是怎么训练出来的，可以看看这个开源项目 MiniMind。
作者声称只需 3 块钱的 GPU 成本、2 小时就能完成一个 64M 参数小模型的一轮 SFT 训练。
jingyaogong/minimind
391 views
想搞懂大模型怎么训练？MiniMind 把全流程摊开了。
原生 PyTorch 实现，预训练、SFT、LoRA、DPO 全有，PPO/GRPO、工具调用和 Agent 强化学习也在里面。代码精简，能边读边跑。
我原本以为又是调 API 的壳，结果是真训练代码。
仓库：jingyaogong/minimind
64M 参数的小模型，你打算先跑哪一段？ t.co
16 views
4 репозитория недели: своя ИИ-модель с нуля меньше чем за 50 центов
4 репозитория недели. В одном ты обучаешь свою ИИ-модель с нуля меньше чем за 50 центов.
1. Агент для кода на любой модели: Twigpine/openclaude
2. Класс ИИ-учителей: THU-MAIC/OpenMAIC
3. Навыки для исследований: Imbad0202/academic-research-skills
4. Своя модель с нуля: jingyaogong/minimind
Открой Claude Code, вставь ссылку и напиши: «Поставь это и покажи на примере».
Для MiniMind сначала спроси Claude: «Хватит ли моей видеокарты, или лучше арендовать?»
Нужна подписка Claude Pro или Max. Для MiniMind видеокарта NVIDIA или аренда на 2 часа.
Бесплатная игра и материалы из всех роликов: ig.onai.academy
#shorts #github #нейросети #ии
16 likes · 1 comment · 1,057 views
与其看十篇千篇一律的源码解析文章，不如花杯奶茶钱亲手从 0 到 1 炼出一个属于自己的小模型。
项目地址：jingyaogong/minimind
项目主页：jingyaogong.github.io
面试或实战大模型岗位时，你觉得“深入手写过底层训练循环”相比“熟练使用主流微调框架”，哪个含金量更高？
3 likes · 274 views
花 4 元、用 2 小时，就能从零训练一个 64M 小模型？
开源项目 MiniMind 用原生 PyTorch 实现了预训练、SFT、LoRA、DPO、PPO/GRPO 及 Agent 训练等流程，模型结构对齐 Qwen3，个人也能动手复现。
想搞懂大模型训练原理，这个项目值得研究。
🔗 GitHub：jingyaogong/minimind t.co
7 likes · 691 views
想从零训练大模型？不用一上来就烧钱堆算力！
GitHub 6.3 万 Star 的 MiniMind，把预训练、SFT、LoRA、DPO 等训练流程做成了可运行的 PyTorch 代码，最小语言模型仅 25.8M 参数。
还有视觉模型 MiniMind-V，想研究大模型底层原理的值得收藏。
🔗 jingyaogong/minimind t.co
2 likes · 1 repost · 147 views
Mentions
5 Free AI Repos: The Code Is Free, Running It Isn't Five free AI repos: the code is free, running it isn't. Here's the real bill for each, compute, services and licence (figures at time of filming, checked 23 Oct 2026). Not a dunk: all five are genuinely useful, just check the needs and the licence first. MiniMind (Apache-2.0): its headline is a tiny ~64M-parameter language model in about 2 hours on a single NVIDIA RTX 3090 (the README's footnote: 2 hours is one epoch of the SFT stage) for about RMB 3 of server cost. Free code, but you need (or rent) a GPU. OpenClaude: its LICENSE says the repo contains code derived from the proprietary Claude Code CLI; the community changes are MIT only "where legally permissible", and GitHub shows the licence as NOASSERTION. Read the licence before you build on it. OpenMAIC (MIT): the server needs a PostgreSQL database (DATABASE_URL) plus an AI model provider. Cloud models need an API key (billed by the provider); a local model through Ollama doesn't. Academic Research Skills (CC BY-NC 4.0, non-commercial): runs inside paid Claude Code with API keys; the author estimates about US$3–7 per 15,000-word paper, and in their own test 21 of 68 references had problems, so check every citation. Invidious (AGPL-3.0): an alternative YouTube front end; its docs list just five public clearnet instances, so you may end up self-hosting a server. Which one is worth the hassle? Sources (all public, no need to comment for them): MiniMind: jingyaogong/minimind OpenClaude: Twigpine/openclaude OpenMAIC: THU-MAIC/OpenMAIC OpenMAIC setup docs: open.maic.chat Academic Research Skills: Imbad0202/academic-research-skills Invidious: iv-org/invidious Invidious public instances: docs.invidious.io #AI #OpenSource #GitHub #shorts Made with AI-generated visuals and voice.
想自己搞个 AI 小玩具玩玩，还能顺便研究一下大模型到底是怎么训练出来的，可以看看这个开源项目 MiniMind。 作者声称只需 3 块钱的 GPU 成本、2 小时就能完成一个 64M 参数小模型的一轮 SFT 训练。 jingyaogong/minimind
想搞懂大模型怎么训练？MiniMind 把全流程摊开了。 原生 PyTorch 实现，预训练、SFT、LoRA、DPO 全有，PPO/GRPO、工具调用和 Agent 强化学习也在里面。代码精简，能边读边跑。 我原本以为又是调 API 的壳，结果是真训练代码。 仓库：jingyaogong/minimind 64M 参数的小模型，你打算先跑哪一段？ t.co
4 репозитория недели: своя ИИ-модель с нуля меньше чем за 50 центов 4 репозитория недели. В одном ты обучаешь свою ИИ-модель с нуля меньше чем за 50 центов. 1. Агент для кода на любой модели: Twigpine/openclaude 2. Класс ИИ-учителей: THU-MAIC/OpenMAIC 3. Навыки для исследований: Imbad0202/academic-research-skills 4. Своя модель с нуля: jingyaogong/minimind Открой Claude Code, вставь ссылку и напиши: «Поставь это и покажи на примере». Для MiniMind сначала спроси Claude: «Хватит ли моей видеокарты, или лучше арендовать?» Нужна подписка Claude Pro или Max. Для MiniMind видеокарта NVIDIA или аренда на 2 часа. Бесплатная игра и материалы из всех роликов: ig.onai.academy #shorts #github #нейросети #ии
与其看十篇千篇一律的源码解析文章，不如花杯奶茶钱亲手从 0 到 1 炼出一个属于自己的小模型。 项目地址：jingyaogong/minimind 项目主页：jingyaogong.github.io 面试或实战大模型岗位时，你觉得“深入手写过底层训练循环”相比“熟练使用主流微调框架”，哪个含金量更高？
花 4 元、用 2 小时，就能从零训练一个 64M 小模型？ 开源项目 MiniMind 用原生 PyTorch 实现了预训练、SFT、LoRA、DPO、PPO/GRPO 及 Agent 训练等流程，模型结构对齐 Qwen3，个人也能动手复现。 想搞懂大模型训练原理，这个项目值得研究。 🔗 GitHub：jingyaogong/minimind t.co
想从零训练大模型？不用一上来就烧钱堆算力！ GitHub 6.3 万 Star 的 MiniMind，把预训练、SFT、LoRA、DPO 等训练流程做成了可运行的 PyTorch 代码，最小语言模型仅 25.8M 参数。 还有视觉模型 MiniMind-V，想研究大模型底层原理的值得收藏。 🔗 jingyaogong/minimind t.co