Tag
A Hugging Face blog walks through how a user built six custom small models in a couple of days by prompting the ML Intern agent, including a 0.8B CPU-friendly distillation of Qwen-Image 2.1's 9B prompt rewriter for just $16 in compute, and shares the prompting patterns (baseline checks, smoke tests, budget caps) that made it reliable.
Hugging Face is releasing ML Intern in HuggingChat, an AI agent that simplifies model training by handling the entire process from conversation to shareable artifacts on the Hub.
The article reassures that a potential acquisition won't compromise open-source commitments and introduces ML Intern, a new tool in HuggingChat that enables ML builders to create models and apps through conversation.
Hugging Face open-sourced ml-intern, an autonomous agent that performs the entire ML post-training loop—reading papers, finding datasets, writing scripts, generating data, monitoring training, and uploading weights—achieving significant GPQA improvement with a 1.7B model in 10 hours without human intervention.
The ml-intern project from Hugging Face has gone viral on GitHub, enabling full automation of the entire workflow including paper research, data processing, training script writing, and model training, without human intervention. It significantly improves the performance of small models (such as Qwen3-1.7B), even surpassing Claude Code.
Trained a prompt injection classifier using ml-intern and DeepSeek V4 Flash, achieving 99% F1 with DistilBERT, optimized to ONNX int8 (~65MB) and deployable in the browser via Transformers.js v3.
Hugging Face open-sourced ml-intern, an autonomous agent that reads ML papers, discovers datasets, trains models, debugs failures, and ships production-ready models to the Hub, automating the entire post-training workflow.
Developer praises ml-intern tool for streamlining model/dataset discovery, post-training iteration and data workflows.