想自己微调 LLM，最折磨人的往往不是训练，而是环境配置。
![想自己微调 LLM，最折磨人的往往不是训练，而是环境配置。 Soup 把流程压到三步： pip install "soup-cli[train]" → soup init --template chat → soup train 一个…](https://pbs.twimg.com/media/HSas4nRbIAAODqr.png?name=large)
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
想自己微调 LLM，最折磨人的往往不是训练，而是环境配置。 Soup 把流程压到三步： pip install "soup-cli[train]" → soup init --template chat → soup train 一个 YAML 配置文件搞定训练。 1️⃣ 支持聊天、代码、推理、视觉、RLHF 等多种模板 2️⃣ 通过 Layer Streaming 降低显存占用 3️⃣ 4GB 显存也能尝试微调 8B 模型 4️⃣ 训练后可导出 GGUF，直接接 Ollama，也能推到 Hugging Face 它更有意思的地方是：把原本一堆服务器、驱动和参数调试的流程，尽量压缩成了一个 CLI 工作流。 想折腾自己的模型，门槛低了不少。 🔗 https://github.com/MakazhanAlpamys/Soup
Posted by lumxss (24.7k followers) 2 days ago · 16 likes · 1.4k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: soup.
More dev work like this
- 💥什么鬼！本地开源 Jev 居然杀到了 0 输出 Token，自带三档模型直接落地结构化判断！ — @NFT_Chen
- AI Agent System for Deep Learning Model Migration from TensorFlow to JAX! #BigData… — @gp_pulipaka
- Vectorizing the Math for LLM! #BigData #Analytics #DataScience #AI #MachineLearning #IoT… — @gp_pulipaka
- Hermes Wingtips #79: `agent[.]disabled_toolsets` — @witcheer
- Give your coding agent a box — not your whole machine. — @DanKornas
- it's awesome to see the reception here 🔥 — @jerryjliu0
- 🌙 中秋福利续上！OpenCode 官方再延长一周！DeepSeek V4.1 Flash 的 4 倍额度已延至 9 月 27 日，完美覆盖中秋！ — @NFT_Chen
- 🚨 Step 5 Preview — @chetaslua
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 18.9k posts from 4.9k X accounts over the last 21 days, 2.1k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 06:12 UTC. Full method.