Liquid AI Cookbook: Fine-Tuning LFMs with CPT, SFT, DPO and GRPO

Melvin Vivas · X post · 2026-08-11 · Open on X

Topics: Fine-tuning & Model Customization · Level: intermediate

Summary

Melvin Vivas recommends the Liquid AI cookbook as a strong, underrated resource for fine-tuning Liquid's LFM models. It covers text, vision, audio and encoder models. It also covers several training methods (CPT, SFT, DPO, GRPO) using Unsloth or Hugging Face TRL.

Key points

• The Liquid AI cookbook covers fine-tuning text, vision, audio and encoder models.
• Training methods covered: continued pretraining (CPT), supervised fine-tuning (SFT), DPO and GRPO.
• Examples use Unsloth or Hugging Face TRL to fine-tune LFM (Liquid Foundation Model) models.

Resources mentioned

• Liquid AI Cookbook · repo · github.com · free
  Liquid AI's collection of fine-tuning examples for LFM models across modalities and training methods.
• Liquid AI (@liquidai) on X · website · x.com · free
  An AI company that builds efficient foundation models. The quoted post shows its PII handling working on Japanese text.
  Also in: Zero-Shot Prompt Routing with Liquid AI's LFM 2.5-Encoder-350M (Melvin Vivas on X · notes), Liquid AI LFM 2.5 Encoder: a CPU-friendly encoder model (Melvin Vivas on X · notes), Fine-tuning Liquid AI LFM2/LFM2.5 MoE models with the new Halo framework (Melvin Vivas on X · notes), Liquid AI's LFM2-Longevity models for aging-data analysis (Melvin Vivas on X · notes) and 19 more
• Unsloth · tool · unsloth.ai · free
  Open-source library for fast, memory-efficient fine-tuning of open LLMs (LoRA/QLoRA) on a single GPU or in Colab.
  Also in: Run Laya Decision models locally with Unsloth on 4GB RAM (Melvin Vivas on X · notes), Unsloth passes 500M model downloads on Hugging Face (Melvin Vivas on X · notes), Run Qwen-Image-2.1 locally on 12GB VRAM with Unsloth GGUFs (Melvin Vivas on X · notes), Base vs fine-tuned Gemma 4 E2B as a model router (Melvin Vivas on X · notes) and 29 more
• TRL (Hugging Face) · tool · github.com · free
  Hugging Face's open-source library for post-training LLMs with SFT, DPO, GRPO and more.
  Also in: Fine-Tune LFM2.5-350M with GRPO in TRL for Structured Outputs (Melvin Vivas on X · notes)

Try this

• Work through the Liquid AI cookbook to practise SFT, DPO or GRPO on a small LFM model.
• Fine-tune a small LFM model with SFT and then DPO using Unsloth or TRL, following the cookbook.