Ifeval score 55 on inst-level loose-accuracy.
#70 opened 6 days ago
by
Jamesunnc
Upload hokm96.xlsx
#69 opened 6 days ago
by
ashkanpourali
poor south west Asia languages
1
#68 opened 9 days ago
by
rastegar
Sliding Window Attention
#67 opened 10 days ago
by
cferggie

Update README.md
#66 opened 12 days ago
by
sujiij
使用react agent解决复杂问题时只会调用一次函数
1
#64 opened 13 days ago
by
tyler1990
reasoning dead loop.
#63 opened 13 days ago
by
creampx

Seeking Advice on Fine-tuning QWQ-32B Model
2
#62 opened 17 days ago
by
aaditya

Steps to deploy a production ready service for QwQ on AWS using serverless GPUs
#61 opened 18 days ago
by
samagra14
Etude
#60 opened 20 days ago
by
Nino-ogvng

Upload gen_ai(proj_47).ipynb
#59 opened 20 days ago
by
harshith1411

How does LiveCodeBench test?
3
#58 opened 24 days ago
by
cizhenshi
Create test
2
#57 opened 24 days ago
by
Amyww

Upload 99ed5d4766696bd4ebc26e5d9c23e982.png
1
#56 opened 24 days ago
by
axingd
Best practice for QwQ-32B evaluation
3
#55 opened 25 days ago
by
wangxingjun778

Create test.txt
#54 opened 26 days ago
by
xxxx443117

How to continue pt / sft on this model,any suggestions?
4
#53 opened 26 days ago
by
Ken0102030405
Infinite repetitive thinking for this case:
1
#52 opened 27 days ago
by
zhaocc1106
Is QwQ-32B used for custom NER extraction? Does this model work better compared to other open-source BERT transformers?
1
#51 opened 27 days ago
by
amiirhmza
Budget forcing?
1
#50 opened 28 days ago
by
mwettach
Allow prefilling assistant message
1
#49 opened 29 days ago
by
tomasmcm

Update README.md
#48 opened 29 days ago
by
Bschleter
Day of the week
#47 opened 29 days ago
by
jac-jim
Intermittent CUDA error with model.generate() using device_map="auto" and 3 GPUs
#46 opened 30 days ago
by
lucmaz98
Create Call Center Tunaiku 0818836245
#45 opened 30 days ago
by
Jokiio
Does Macbook M1 max 64GB run this model well?
1
#44 opened 30 days ago
by
mrk83
Too many "cross-validate" and "another method"
2
#43 opened 30 days ago
by
AaronFeng753
RuntimeError: Error(s) in loading state_dict for Qwen2ForCausalLM:
1
#42 opened 30 days ago
by
XuehangCang

8GB GPU can run this,10t/s
2
#41 opened about 1 month ago
by
wqerrewetw
When answering questions in Chinese, the model frequently terminates prematurely (outputs the end token). Is this a common problem?
1
#40 opened about 1 month ago
by
zhangw355
Refining QWQ Model Output: Direct Responses Without Step-by-Step Reasoning
1
#39 opened about 1 month ago
by
gslinx
It's challenging for QwQ to generate long codes...
2
#38 opened about 1 month ago
by
DXBTR74
Nice work... Cant-believe-its-just-32B-performance even with various different tones system prompt.
#37 opened about 1 month ago
by
imoc
function call时有办法跳过think吗?
2
#36 opened about 1 month ago
by
zhaocc1106
Failed to parse Jinja template:
2
#35 opened about 1 month ago
by
Vicnent

Obligatory question about model sizes...
#34 opened about 1 month ago
by
MrDevolver

This model beats Qwen Max!
6
#33 opened about 1 month ago
by
MrDevolver

remove part about long context modifications
#32 opened about 1 month ago
by
nbroad

add a reasoning effort option
1
#31 opened about 1 month ago
by
TheBigBlockPC
用vllm时应该是什么参数
6
#30 opened about 1 month ago
by
daiwk
遇到复杂问题时,开始推理时有<think>,推理结束了还没有</think>
6
#29 opened about 1 month ago
by
digits12
Is this model native 128K context length, or YaRN extended?
7
#28 opened about 1 month ago
by
danielhanchen

docs: update README.md
#27 opened about 1 month ago
by
eltociear

Thanks a lot for sharing this model!
#26 opened about 1 month ago
by
FalconNet
Doesn't Generate `<think>` tags
3
#25 opened about 1 month ago
by
bingw5
【乱码问题】输入约1w长度,输出超过1000长度,结尾部分会乱码。稳定复现!
1
#24 opened about 1 month ago
by
chizhu

是否需要添加系统prompt
1
#23 opened about 1 month ago
by
wphtrying
A pure C++ high-performance OpenAI LLM service powered by TensorRT-LLM and GRPS, with support for QWQ.
#22 opened about 1 month ago
by
zhaocc1106
复杂推理进入死循环
30
#21 opened about 1 month ago
by
frankgxy