Resources

View closed (6)

How to change the temperature of output generation??

#26 opened 11 days ago by

IronmanSnap

Whats the input syntax for SageMaker endpoint?

#25 opened about 2 months ago by

Pelmenchik

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cuda:0)

#24 opened about 2 months ago by

zkkz17

尝试了一下Qwen2-VL-2B-Instruct

#23 opened 4 months ago by

jiuzhan

qwen2-vl-2b Image features and image tokens do not match

#22 opened 4 months ago by

novicetyro

IndexError: index 0 is out of bounds for dimension 0 with size 0

#21 opened 4 months ago by

saika1997

How to do batch inference on Qwen2-VL-2B-Instruct?

#20 opened 4 months ago by

dutta18

Can't spin this up in SageMaker

#19 opened 4 months ago by

Pelmenchik

inference time and memory usage of quantized version

#18 opened 5 months ago by

DILLIP-KUMAR

ImportError: cannot import name 'Qwen2VLForConditionalGeneration' from 'transformers'

#17 opened 6 months ago by

MM-11

it run on cpu

#15 opened 7 months ago by

sdyy

How to use on multiple gpus?

#12 opened 7 months ago by

Chan-Y

How to use this for thousands of image with a good speed?

#11 opened 7 months ago by

the-sanyam

Hardware requirements

#10 opened 7 months ago by

ZahirHamroune

Update README.md

#9 opened 7 months ago by

Chan-Y

Failed to load Qwen2-VL using transformers built version(60226fd)

#7 opened 7 months ago by

Zoey1024

Update generation_config.json

#6 opened 7 months ago by

apanasenko

is the Custom handler.py File something i create myself? because looks like the qwen models dont come with it?

#5 opened 8 months ago by

whosii

gguf

#4 opened 8 months ago by

goodasdgood

mistakes

#3 opened 8 months ago by

goodasdgood