Qwen 3 presence of tools affect output length?
#17 opened about 5 hours ago
by
evetsagg
"/no_think" control is unstable
1
#16 opened about 8 hours ago
by
Smorty100
⛔ Censored on Chinese political regime topics. Sad for the model cohesion.
#15 opened about 10 hours ago
by
owao
LICENSE files missing
#14 opened about 14 hours ago
by
johndoe2001
After setting /nothinking or enable_thinking=False, can the empty <thinking> tag be omitted from the response?
3
1
#13 opened about 21 hours ago
by
pteromyini
Feedback: It's a good model, however it hallucinates very badly at local facts (Germany)
6
1
#12 opened about 22 hours ago
by
Dampfinchen
The correct way of fine-tuning on multi-turn trajectories
2
#11 opened 1 day ago
by
hr0nix
Providing a GPTQ version
3
2
#10 opened 1 day ago
by
blueteamqq1
how to set, enable_thinking=False, on ollama
6
2
#9 opened 1 day ago
by
TatsuhiroC
🚀[Fine-tuning] Implementation and Best Practices for Qwen3 CPT/SFT/DPO/GRPO Training👋
2
#7 opened 1 day ago
by
study-hjt
Reasoning or Non-reasoning model?
4
#6 opened 1 day ago
by
dipta007
Local Installation Video and Testing - Step by Step
#5 opened 1 day ago
by
fahdmirzac
【Evaluation】Best practice for evaluating Qwen3 !!
4
#4 opened 1 day ago
by
wangxingjun778
Base Model?
1
4
#3 opened 1 day ago
by
Downtown-Case
Is this multimodal?
1
#2 opened 1 day ago
by
pbarker
Add languages tag
1
#1 opened 1 day ago
by
de-francophones