Fine-tuning Gemma4-E2B on your own tweet style with Unsloth
Melvin Vivas · X post · 2026-09-19 · Open on X
Topics: Fine-tuning & Model Customization, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator is building a notebook that fine-tunes the small Gemma4-E2B model to write in his own tweet style, using Unsloth. He runs it through a Google Colab plugin inside Devin Desktop. It shows a practical style fine-tune of a small open model on personal data.
Key points
- Small open models like Gemma4-E2B can be fine-tuned to copy a personal writing style (here, the creator's tweets).
- Unsloth is the fine-tuning library used for the training notebook.
- Training runs in a notebook through a Colab plugin, so it uses cloud GPUs instead of local hardware.
- The notebook was written inside Devin Desktop, an AI coding tool that has a Colab plugin.
Resources mentioned
- 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: 100-Iteration Autonomous Coding Loop with Local Qwen on an RTX 3090 (Melvin Vivas on X · notes), Prompting an Autonomous Agent Loop: Be Specific, Show Visible Progress (Melvin Vivas on X · notes), Running an Overnight 100-Iteration Agent Loop with a Local Qwen Model (Melvin Vivas on X · notes), Agent tasks: Unsloth fine-tuning, ComfyUI face swap, script writing (Melvin Vivas on X · notes) and 36 more - Gemma 4 · tool · ai.google.dev · free
Google's family of open-weight models in several sizes, built to run on devices and offline, with multimodal and agentic abilities, and open to fine-tuning.
Also in: Meetily: Open-Source Local AI Meeting Notes App (Melvin Vivas on X · notes), New Gemma Developer Documentation Site (Melvin Vivas on X · notes), A100 80GB GPUs in Google Colab via Google AI Pro plans (Melvin Vivas on X · notes), A day of work done from a phone with Grok Bot agents (Melvin Vivas on X · notes) and 32 more - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Google Colab notebooks for new open models, built by a coding agent (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes) and 27 more - Devin Desktop (@devindesktop) · tool · x.com · free · open in a browser to verify
Desktop app for the Devin AI coding agent. The linked X profile returned 'not found' when checked.
Also in: Devin's SWE-2 model is free on paid plans for a limited time (Melvin Vivas on X · notes), Devin's kanban view for monitoring running agents (Melvin Vivas on X · notes), SWE-2 Is Currently Free in Devin Desktop (Melvin Vivas on X · notes), GLM 5.2 Is Fast and Free in Devin Desktop (Melvin Vivas on X · notes)
Try this
- Fine-tune a small open model (e.g. Gemma4-E2B) with Unsloth on your own tweets or posts so it writes in your style.
More in Fine-tuning & Model Customization
- Base vs fine-tuned Gemma 4 E2B as a model router
- QLoRA fine-tune Gemma 4 E2B with Unsloth as a model router
- Free Colab Notebooks: ModernBERT, Gemma QLoRA, GLiNER & Guardrails
- Not every problem needs an LLM: small fine-tuned models (Jev by TypeSafe AI)
- Hugging Face AutoTrain: a no-code fine-tuning tool
- LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio