Resources

View closed (15)

A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone ? Which model variant?

#33 opened 4 days ago by

nezwork123

ImportError: libcudart.so.11.0: cannot open shared object file: No such file or directory

#31 opened 2 months ago by

GrimPeaPer

Can this model do OCR/object detection with region bound box?

#30 opened 2 months ago by

pacozaa

Error: Matmul multiplication error

#29 opened 2 months ago by

supercharge19

no-flash-attn

#27 opened 3 months ago by

hemanham

Update modeling_navit_siglip.py

#26 opened 3 months ago by

toilaluan

What's the chat prompt template in plain text?

#25 opened 3 months ago by

apepkuss79

Demo UI vs Inference in code

#24 opened 3 months ago by

WoutDeRijck

Hanldler.py file not found

#23 opened 3 months ago by

SwatiM

Hyper params used in demo UI vs Inference via ciode

#22 opened 3 months ago by

nezwork123

Flash Attention Issue

#21 opened 3 months ago by

Machlovi

Siglip: add _no_split_module

#20 opened 3 months ago by

eddtsoi

How can I batchfy my input (img, questions) to the model?

#19 opened 3 months ago by

dingbang777

readme.me

#18 opened 3 months ago by

BRSIOFT

如何解决错误：RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

#13 opened 4 months ago by

lele12306

Use lazy import for flash_attn

#12 opened 4 months ago by

HwwwH

remove flash_attn dependency for macos / non-gpu machines

#9 opened 4 months ago by

ursnation

🍭 Best Practice for Inference and Fine-Tuning of MiniCPM-V 2.6

#2 opened 4 months ago by

study-hjt