First LoRA Run on Qwen3.5-2B with Codex as Training Companion

Melvin Vivas · X post · 2026-09-14 · Open on X

Topics: Fine-tuning & Model Customization, AI Dev Tools & Productivity · Level: intermediate

Summary

The creator finished his first fine-tuning run of Qwen3.5-2B to copy his tweet style. Codex helped throughout and showed him where to change settings in Unsloth Studio.

Key points

• Fine-tuned Qwen3.5-2B on his own tweets to copy his writing style.
• Used Codex as a companion during training. It pointed him to the right settings in Unsloth Studio.

Resources mentioned

• OpenAI Codex · tool · openai.com · paid
  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: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 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
• Qwen3.5-2B · tool · huggingface.co · free
  Small open-weight Qwen language model, used here as the base for fine-tuning.
  Also in: LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio (Melvin Vivas on X · notes), Post-training Qwen3.5-2B on your own X posts with Unsloth Studio (Melvin Vivas on X · notes), Fine-Tuned Qwen3.5-2B LoRA Model That Writes X Posts in Your Style (Melvin Vivas on X · notes)

Try this

• Use a coding agent like Codex to guide you through configuring a fine-tuning run in Unsloth Studio.
• Fine-tune a small model on your tweets to copy your writing style.