Smoke-Testing LFM Fine-tuning with Codex and Liquid AI's LEAP
Melvin Vivas · X post · 2026-08-11 · Open on X
Topics: Fine-tuning & Model Customization, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator is trying out fine-tuning Liquid AI's LFM models with the LEAP framework, using Codex as a coding assistant. He starts with a 100-row smoke-test dataset to get a feel for the workflow. It shows a cheap way to check a fine-tuning pipeline before scaling up.
Key points
- Run a smoke test with a tiny dataset (about 100 rows) before a full fine-tuning run.
- A smoke test checks data format, the training loop and outputs quickly and cheaply.
- Liquid AI's LEAP framework can be used to train and fine-tune LFM models.
- A coding agent like Codex can help write and run the fine-tuning scripts.
Resources mentioned
- Liquid AI (@liquidai) on X · website · x.com · free
Liquid AI's family of efficient foundation models, used here as the example of a model you can run in the browser with ONNX.
Also in: Trying Liquid AI Decision Models (d1, d1 ultra) via API (Melvin Vivas on X · notes), Liquid RIPL: Low-Latency Inference Engine for LFMs (Melvin Vivas on X · notes), ONNX + Transformers.js: Run Models Like Liquid LFM in the Browser (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes) and 30 more - LEAP (Liquid AI) · tool · leap.liquid.ai · check price
Liquid AI's framework for fine-tuning and customizing its small models.
Also in: Small Local Models + Fine-Tuning Instead of More Compute (Liquid AI, LEAP) (Melvin Vivas on X · notes), LFM2.5-2.6B Matches DeepSeek-V4-Flash on Tool Calling; LEAP Fine-Tuning (Melvin Vivas on X · notes) - Liquid Foundation Models (LFM) · tool · liquid.ai · free
Liquid AI's family of efficient foundation models that can be fine-tuned. - OpenAI Codex · tool · openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: Developers moving from ChatGPT/Codex to Claude (Melvin Vivas on X · notes), Creator Opinion: Codex Is Still the Best at Computer Use (Melvin Vivas on X · notes), OpenAI Codex Ambassador applications are open (Melvin Vivas on X · notes), GPT-Live-1.1: Multilingual Voice Update for ChatGPT and Codex (Melvin Vivas on X · notes) and 264 more
Try this
- Smoke-test your fine-tuning pipeline on about 100 rows before a full training run.
- Fine-tune a small Liquid AI LFM model on a custom dataset using LEAP, with a coding agent writing the training scripts.
More in Fine-tuning & Model Customization
- Fine-Tune Muse Glimmer 30B with LoRA or Full-Parameter on Fireworks
- jsonl-viewer: view and edit JSONL fine-tuning datasets
- Fine-Tune Muse Glimmer 30B for Free with Unsloth (incl. GRPO)
- Free JSONL Viewer for Inspecting Fine-tuning Datasets
- Liquid AI Cookbook: Fine-Tuning LFMs with CPT, SFT, DPO and GRPO
- Loop engineering fits fine-tuning better than coding