openbmb/MiniCPM-Llama3-V-2_5

#54 opened about 1 year ago by

Zoitd

Fix task name

#53 opened about 1 year ago by

merve

About LLaVA Bench

#52 opened about 1 year ago by

Pistachioo

OCR问题

#51 opened about 1 year ago by

william0014

Anybody know how/what can actually load/inference this model?

4

#50 opened about 1 year ago by

SytanSD

I want to know the textual context length of this model

#48 opened about 1 year ago by

vobbilisettyjayadeep

couldn't connect to 'https://hf-mirror.com'

#47 opened about 1 year ago by

ccccccyan

How does MiniCPM-Llama3-V 2.5 OCR functions compared with ABBYY?

#46 opened about 1 year ago by

DouglasZHANG

gguf / llama.cpp support

#45 opened about 1 year ago by

cmp-nct

feat: Added judgment logic to support training with plain text data.

#42 opened over 1 year ago by

PaceWang

关于openai compatible api

#41 opened over 1 year ago by

weiminw

Deploying the model to Amazon Sagemaker for "inference"

#40 opened over 1 year ago by

Shan097

The Kernel crashed while executing code in the current cell or a previous cell.

#34 opened over 1 year ago by

Entz

[AUTOMATED] Model Memory Requirements

#33 opened over 1 year ago by

model-sizer-bot

failed to load model in LM Studio 0.2.24

#32 opened over 1 year ago by

skzz

Helpme

#30 opened over 1 year ago by

HamBoneTheSniff

Is there any tuturial for inference with batch_size > 1?

👍 👀 6

#29 opened over 1 year ago by

virtueai-mz

为什么回答是乱码？/Why is the response garbled?

#28 opened over 1 year ago by

z784721485

will there be doc for introducing details of the dataset and training strategies?

#27 opened over 1 year ago by

stiffxj

Potential bug when batch inferencing with left padding.

🚀 5

#26 opened over 1 year ago by

Snorlax

Why doesn't it work with bitsnbytes 8 or 4bit?

🔥 1

#25 opened over 1 year ago by

jackboot

Latest Code

#24 opened over 1 year ago by

Taylor658

llama3-V project is stealing a lot of academic work from MiniCPM-Llama3-V 2.5 ！

🤯 👍 3

10

#23 opened over 1 year ago by

pzc163

finetune

6

#22 opened over 1 year ago by

deqiuqiuzhang

Quite exceptional - looking forward to see the fork implemented in llama.cpp - but why that fork choice ?

#20 opened over 1 year ago by

cmp-nct

Why 'trust_remote_code=True' ? What remote code is being executed ?

#17 opened over 1 year ago by

Kkordik

Mobile App?

#16 opened over 1 year ago by

Yhyu13

总结几个重点问题：