用vllm时应该是什么参数
6
#30 opened about 1 year 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>
7
#29 opened about 1 year ago
by 
digits12
Is this model native 128K context length, or YaRN extended?
7
#28 opened about 1 year ago
by 
danielhanchen
docs: update README.md
#27 opened about 1 year ago
by 
eltociear
Thanks a lot for sharing this model!
❤️ 5
#26 opened about 1 year ago
by 
FalconNet
Doesn't Generate `<think>` tags
3
#25 opened about 1 year 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 year ago
by 
chizhu
是否需要添加系统prompt
1
#23 opened about 1 year 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 year ago
by 
zhaocc1106
复杂推理进入死循环
30
#21 opened about 1 year ago
by 
frankgxy
I've tried it, the locally deployed 8G4060 can run, it's just a bit slower.
➕👍 7
2
#20 opened about 1 year ago
by 
Alta007
Off the charts - GREAT JOB!
1
#17 opened about 1 year ago
by 
DavidAU
Where can I see the GPQA for this model?
1
#16 opened about 1 year ago
by 
capgrey
issue of "think too much" ，how to？(chinese)
2
#14 opened about 1 year ago
by 
fenglui
Local Installation Video - Step-by-Step Tutorial
🔥 5
#13 opened about 1 year ago
by 
fahdmirzac
Tool-Calling Format
🚀 1
1
#12 opened about 1 year ago
by 
G-reen
我的3090TI 24GB显存运行非常愉快！感谢开发团队！
👍🚀 14
6
#11 opened about 1 year ago
by 
ubergarm
add missing special tokens in tokenizer.json
➕ 3
#10 opened about 1 year ago
by 
mmoskal
Is `rms_norm_eps` 1e-5 or 1e-6
#9 opened about 1 year ago
by danielhanchen
Oh My NVDA Position
🔥🤯 3
1
#8 opened about 1 year ago
by 
Eric2i
What languages were you trained in?
👍 1
2
#7 opened about 1 year ago
by 
NickyNicky
You guys are the pioneers!
#6 opened about 1 year ago
by 
owao
missing opening <think>
20
#4 opened about 1 year ago
by 
chriswritescode
One Of Many
🔥 2
#3 opened about 1 year ago
by 
nanowell
Is system prompt required?
👍 1
1
#2 opened about 1 year ago
by 
baohao