NEWS · MODELS · #1748
User automates fine-tuning and publishing of multiple small models using 'ML-intern' on Hugging Face Hub
A user reports using a conversational agent called ML-intern via HuggingChat to plan, budget, fine-tune, evaluate and publish several task-specific models and LoRAs on the Hugging Face Hub. Examples include a CPU-runnable 0.8B prompt-rewriter distilled from a 9B Qwen model, a Qwen3.5-2B fine-tuned 'citrus-disease-vlm-instruct' dataset model (base 14.9% → fine-tuned 52.8% on a 335-photo test; ~USD 1.90), and a Huggy LoRA trained on 84 drawings (compute ~USD 7.60); the author says the whole project’s compute including 8,797 example labels cost about USD 16.
KEY POINTS
- A user reports using a conversational agent called ML-intern via HuggingChat to plan, budget, fine-tune, evaluate and publish several task-specific models and LoRAs on the Hugging Face Hub.
- Examples include a CPU-runnable 0.8B prompt-rewriter distilled from a 9B Qwen model, a Qwen3.5-2B fine-tuned 'citrus-disease-vlm-instruct' dataset model (base 14.9% → fine-tuned 52.8% on a 335-photo test; ~USD 1.90), and a Huggy LoRA trained on 84 drawings (compute ~USD 7.60); the author says the whole project’s compute including 8,797 example labels cost about USD 16.
- This demonstrates an agentic workflow that can cheaply automate dataset preparation, fine-tuning, evaluation and Hub publication, lowering the barrier to producing small, task-specific models.
WHY IT MATTERS
This demonstrates an agentic workflow that can cheaply automate dataset preparation, fine-tuning, evaluation and Hub publication, lowering the barrier to producing small, task-specific models.