jklj077
jklj077
AI & ML interests
None yet
Organizations
jklj077's activity
bos_token==pad token??
2
#3 opened 1 day ago
by
Jerry-hyl
load from local filepath error
1
#2 opened 1 day ago
by
bdambrosio
Licence?
1
#1 opened 1 day ago
by
migtissera
Language
1
#5 opened about 24 hours ago
by
forwins
What dose A14 means? Could we get the detail of Qwen MOE architechture?
2
#1 opened 1 day ago
by
JohnSaxon
请问template模版更换了么
1
#4 opened 1 day ago
by
okcwang
bos_token_id == pad_token_id?
1
#1 opened 1 day ago
by
nlev
tokenizer model?
1
#2 opened 1 day ago
by
bdambrosio
Qwen2-72B-Instruct max_position_embedding is 32768?
1
#3 opened 1 day ago
by
cizhenshi
tie_word_embeddings=true ?
1
#6 opened about 2 months ago
by
salmitta
Why 72B model has different vocab size comparing with other models?
3
#1 opened 4 months ago
by
Mikasaka
不同型号的GPU能否运行qwen72b-int4
1
#11 opened 3 months ago
by
XCZDH
License clarity, please.
1
#3 opened 3 months ago
by
computerdarren
qwen72B有awq的量化版本吗?
1
#5 opened 3 months ago
by
dongxq
While inputting text prompt and my custom image, when i submit the image i got error response
1
#8 opened 3 months ago
by
aliman80
Error on submit
3
#2 opened 4 months ago
by
alx-ai
Error when sending message
3
#13 opened 3 months ago
by
lissthings01
The model gives error messages when I upload model.
3
#7 opened 3 months ago
by
AdemSkr
constantly outputting tokens
1
#4 opened 3 months ago
by
nogggg
模型在A10上推理的时候如果设置了temperature会报错
2
#9 opened 3 months ago
by
richard-yao
推理速度有些慢
3
#3 opened 3 months ago
by
yaoye7758521
Update README.md
#3 opened 2 months ago
by
Crystalcareai
Why is there only one shared expert in the code?
2
#4 opened 2 months ago
by
KevinChen1994
虽然支持32768的上下文但是为啥输入token大于4k就会报oom的错误???
2
#4 opened 3 months ago
by
hellohaitao
How is the inference so fast in this free hardware space?
2
#1 opened 2 months ago
by
mahiatlinux
how to finetune and quantize the qwen1.5 model with gguf
1
#5 opened 2 months ago
by
huntz47
不依赖其他推理框架,多轮对话代码如何实现?是否有使用例子?
1
#10 opened about 2 months ago
by
hongfengvv
missing quantize_config.json file
1
#4 opened about 2 months ago
by
aromo17
how to get the 473M model from Qwen/Qwen1.5-0.5B-Chat
1
#1 opened 3 months ago
by
chengfeng17
qwen1.5-7b-chat是不是推理起来比qwen1.5-7b快很多
3
#9 opened 3 months ago
by
endNone
ValueError: QWenLMHeadModel does not support Flash Attention 2.0 yet.
2
#1 opened 3 months ago
by
sanjeev-bhandari01
had upgraded transformer==4.37.0, the error "KeyError: 'qwen2'" becomes "qwen2 isn't suported yet"
1
#1 opened 3 months ago
by
sdwcn
API key?
2
#9 opened 3 months ago
by
Darius753
demo crash?
1
#2 opened 4 months ago
by
YangJiassh
can't run with fastchat cuda 12.1
2
#1 opened 4 months ago
by
jaywanghz
The attention mask and the pad token id were not set
1
#2 opened 4 months ago
by
areumtecnologia
CUDA extension not installed
2
#1 opened 4 months ago
by
areumtecnologia
本地启动这个app.py出错
1
#6 opened 4 months ago
by
Moses25
TypeError: qwen2 is not supported yet.
2
#1 opened 4 months ago
by
n1ghtbar0n
ValueError: unknown ids
5
#38 opened 9 months ago
by
allenhaozi
AttributeError: 'Qwen2TokenizerFast' object has no attribute 'eod_id'
1
#1 opened 4 months ago
by
interstellarninja
系统指令在哪设置?
1
#6 opened 4 months ago
by
Moses25
finetuning error
1
#12 opened 4 months ago
by
adonlee
On how much English token was the model trained onn
3
#5 opened 5 months ago
by
aslawliet
How did you evaluate the Qwen chat models on MMLU (or any other datasets)
1
#49 opened 5 months ago
by
omers66
Attempt to add in add_ Special_ Tokens, there is an error, how should I solve it
1
#19 opened 5 months ago
by
wangchengfei
Max sequence length config
1
#14 opened 5 months ago
by
alexhsu
issues about config.json and model.py
1
#4 opened 5 months ago
by
J22
Can you please submit this to leaderboard?
6
#15 opened 5 months ago
by
gblazex
有时候会吐出 训练集文本.
10
#2 opened 6 months ago
by
kk3dmax
Is it possible to pad inputs?
2
#2 opened 6 months ago
by
omers66
Training loss?
3
#2 opened 6 months ago
by
borgr
About sft got unstoppable \n when output
1
#10 opened 7 months ago
by
lucasjin
It would be useful if someone spent the time to convert the tokenizer to gpt2 HF format
2
#9 opened 7 months ago
by
KnutJaegersberg
Tokenizer issue
1
#1 opened 9 months ago
by
teknium