Qwen just published the 'Thinking' variant of this model 🔥
So you can run a model EVEN MORE powerful than GPT-4o locally!
- Still only 3B active parameters
- Open source license
- 256k context window extendable to 1M
- Strong in math, science and coding
Details below ↓ https://t.co/QDX4t5EmcC
Here're the perfect settings for this models in LM Studio:
* Min P Sampling: 0
* Repeat Penalty: Disabled
* Temperature: 0.6
* Top K Sampling: 20
* Top P Sampling: 0.95
You can set them in one click (+ the prompt template) here:
https://t.co/7WJS2cMHjY https://t.co/jStUTAVu7I
Useful links:
- Hugging Face: https://t.co/z4c8Ca40SU
- Try it on Qwen Chat: https://t.co/2NoTc5SJJx (click on "Thinking")
One day, one open source model! https://t.co/qvLABBj70O
