The model that didn't exist, so you made it yourself
Last week, I wanted a small version of the prompt rewriter that ships with Qwen-Image 2.1.
Key points
- 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.
- So I described what I wanted to ML Intern, and the next day I had a 0.8B version that runs on a CPU.
- Without it you get a trained model and no idea whether it is better than what you started with.
Sources (1)
- [1]The model that didn't exist, so you made it yourselfHugging Face Blog · Oct 8, 12:00 AM
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.
Extractive summary: sentences quoted from the sources.