Hongji Zhu

#49 opened 3 months ago by

wangli123

What's the chat prompt template?

#73 opened 18 days ago by

apepkuss79

突然加载不了tokenizer了，是不是升级导致的版本不兼容

5

#67 opened about 2 months ago by

Jiiao

Too many bugs and changes

#65 opened about 2 months ago by

IridiumFang

New activity in openbmb/MiniCPM-V-2_6 21 days ago

Siglip: add _no_split_module

#20 opened 25 days ago by

eddtsoi

New activity in openbmb/MiniCPM-V-2_6 22 days ago

Hyper params used in demo UI vs Inference via ciode

#22 opened 23 days ago by

nezwork123

New activity in openbmb/MiniCPM-V-2_6 23 days ago

Flash Attention Issue

#21 opened 24 days ago by

Machlovi

New activity in openbmb/MiniCPM-Llama3-V-2_5 24 days ago

Number?

#10 opened 2 months ago by

bradShopik

Ike

#12 opened 26 days ago by

praff1234

New activity in openbmb/MiniCPM-V-2_6 25 days ago

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

#19 opened 27 days ago by

dingbang777

New activity in openbmb/MiniCPM-V-2_6 28 days ago

Update README.md

#16 opened about 1 month ago by

not-lain

New activity in openbmb/MiniCPM-V-2_6 about 1 month ago

License?

#17 opened about 1 month ago by

odenibo

Does this come in an English speaking version?

#7 opened about 1 month ago by

sdalemorrey

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

#2 opened about 1 month ago by

study-hjt

Add vision_batch_size to avoid cuda OOM

#4 opened about 1 month ago by

finalf0

Fix batch inference when image is None

#6 opened about 1 month ago by

HwwwH

Fix assert

#5 opened about 1 month ago by

HwwwH

Demo doesn't seem to work

#1 opened about 1 month ago by

RoversX

New activity in openbmb/MiniCPM-Llama3-V-2_5 about 2 months ago

error for the latest commit in modeling_minicpmv.py

#60 opened 2 months ago by

safavakili

CUDA out of memory (4090 24G)

#44 opened 3 months ago by

weiminw

adjust image processing for batch output

#63 opened about 2 months ago by

HwwwH

New activity in openbmb/MiniCPM-Llama3-V-2_5-int4 about 2 months ago

Update README.md

#4 opened 4 months ago by

Berenhap

New activity in openbmb/MiniCPM-Llama3-V-2_5 about 2 months ago

Add processor and image processor

#61 opened 2 months ago by

HwwwH

New activity in openbmb/MiniCPM-V-2 2 months ago

refactor

#15 opened 2 months ago by

finalf0

New activity in openbmb/MiniCPM-Llama3-V-2_5 2 months ago

I want to know the textual context length of this model

#48 opened 3 months ago by

vobbilisettyjayadeep

New activity in openbmb/MiniCPM-Llama3-V-2_5 4 months ago

Mobile App?

#16 opened 4 months ago by

Yhyu13

New activity in openbmb/MiniCPM-Llama3-V-2_5-gguf 4 months ago

can you provide F16.gguf ?

5

#1 opened 4 months ago by

praymich

New activity in qualcomm/Llama-v2-7B-Chat 5 months ago

Weights are not present in the repo

11

#1 opened 7 months ago by

julien-c

New activity in openbmb/MiniCPM-V-2 5 months ago

Does this model support batch inference?

#8 opened 5 months ago by

vahyd

GGUF file

#6 opened 5 months ago by

BB8-dev

New activity in qualcomm/OpenAI-Clip 5 months ago

CLIPImageEncoder.so qnn-net-run run on HTP backend failed

#1 opened 5 months ago by

finalf0

New activity in openbmb/MiniCPM-V-2 5 months ago

Multi-turn Conversations with MiniCPM-V: Exploring Single Image Understanding

#3 opened 5 months ago by

JamePeng2023

有一种方法可以使得模型每次使用chat函数的时候回归到其初始状态吗？

#5 opened 5 months ago by

liudesheng

Demo link broken

#2 opened 5 months ago by

iHaag

cannot load your model file

#1 opened 5 months ago by

eycab

New activity in openbmb/MiniCPM-V 7 months ago

RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

#3 opened 7 months ago by

eelang

New activity in openbmb/MiniCPM-V 8 months ago

how to fine tune model?

4

#2 opened 8 months ago by

NickyNicky

Frameworks versions