Hugging Face Blog·· 8 d ago
The model that didn't exist, so you made it yourself
The model that didn't exist, so you made it yourself
AI summary
Last week, I wanted a small version of the prompt rewriter that ships with Qwen-Image 2.1. The official one is a 9B model that needs about 20 GB of memory and thinks for thousands of tokens before writing a single paragraph. On the Hub, I found only compressed copies of that same 9B model.
Selection record
Threshold 60Official, first-handFirst 71Second 78
AdmittedSum of both 149 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：详述用ML Intern智能体训练发布多个AI模型
- Why it was chosen
- Six models built with ML-intern in two days, with every prompt and the full cost breakdown published, ready to adapt to your own training tasks.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co