Instructions to use froggeric/Qwen-Fixed-Chat-Templates with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use froggeric/Qwen-Fixed-Chat-Templates with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen-Fixed-Chat-Templates froggeric/Qwen-Fixed-Chat-Templates
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Python_Search_file breaks the session
#17
by Jokeru1983 - opened
I tested with V13 and V15 and I have to say, Qwen 3.6 27B is on fire. It's really really fast. I don't know why but especially prompt proicessing is 10 times faster.
The biggest issue is that if qwen used Pyton_search_file tool in Codec-cli it breaks the session, after this read times out as well and replace block always fails.
It should be solved in the final v16 release which I have now promoted to official release.
froggeric changed discussion status to closed