MLX
jinja
chat-template
qwen
qwen3.5
qwen3.6
qwen3.8
llama.cpp
lm-studio
vllm
tool-calling
thinking
token-efficient
Instructions to use peculiar-ragdoll/Qwen-Sharp-Chat-Templates with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use peculiar-ragdoll/Qwen-Sharp-Chat-Templates with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen-Sharp-Chat-Templates peculiar-ragdoll/Qwen-Sharp-Chat-Templates
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Usage on Ornith-1.5-35B-A3B
#7 opened about 17 hours ago
by
nonitis
Add a `_default_reasoning_effort` knob and remove the dead `_initial_effort` line (discussion #3)
#6 opened about 24 hours ago
by
gdevenyi
Add a `terse` template kwarg to opt out of the terseness block
#5 opened 1 day ago
by
gdevenyi
README: add vLLM setup and correct the top-level reasoning_effort claim
#4 opened 1 day ago
by
gdevenyi
Make reasoning effort steering more intuitive in the Jinja template
3
#3 opened 3 days ago
by
extrabigmehdi
Froggeric just release the new Qwen-Fixed-Chat-Templates v22
❤️ 2
3
#2 opened 9 days ago
by
lawlietr
Possible enhancemet to avoid problems with tool calling
❤️ 1
1
#1 opened 9 days ago
by
NeoHuggingF