froggeric
/

Qwen-Fixed-Chat-Templates

Model card Files Files and versions

Resources

View closed (76)

merge improvements from Moore2877/Qwen-Fixed-Chat-Templates-llamacpp

#94 opened 1 day ago by

Usage on Ornith-1.5-35B-A3B

#93 opened 2 days ago by

function "content" not defined error in render_content macro

#92 opened 2 days ago by

Add a `_default_reasoning_effort` knob and remove the dead `_initial_effort` line

#91 opened 2 days ago by

README: qualify the official enable_thinking claim, document sticky inline tags and the string-argument fallback

#90 opened 2 days ago by

README: correct vLLM setup and document which thinking-off channels vLLM's parser tracks

#89 opened 2 days ago by

Read the assistant `reasoning` field (vLLM / Responses API name) when rendering history

#88 opened 2 days ago by

Use a single newline between consecutive tool calls (matches official Qwen templates)

#87 opened 2 days ago by

Github Copilot Desktop Canvas

#86 opened 3 days ago by

v22.3 release notes

#85 opened 3 days ago by

v22.2 issue: tools calls are escaping in regular output

#83 opened 3 days ago by

Non-thinking mode: re-rendered history drops the empty think block, so no prompt is a token-prefix of the next (one-line fix)

#80 opened 4 days ago by

LM studio MLX based models

#79 opened 4 days ago by

this template will lower inference speed？

#76 opened 5 days ago by

qwen3x系列模型的工具调用异常情况调研分析报告

#75 opened 7 days ago by

[Bug] Template-controlled thinking toggles break non-streaming vLLM response parsing

#74 opened 7 days ago by

New release: v22.2 (Qwen 3.8 support, reasoning effort steering, and engine fixes)

#68 opened 10 days ago by

Thank you — and some field evidence you might enjoy

#66 opened 19 days ago by