Meituan-AutoML/MobileVLM
Strong and Open Vision Language Assistant for Mobile Devices
PythonApache-2.0
Issues
- 0
- 0
where can I download mm_projector
#51 opened by wuwu-C - 1
About the supply of mm_projector.bin
#44 opened by Bobby-youngking - 8
funtune with lora error
#17 opened by BadUncleBoy - 0
running gguf Mobile VLM on Mac (metal)
#50 opened by rezacopol - 5
llama.c转换mobileLVM-V2报错
#29 opened by shinerdeng - 0
sft loss curve
#49 opened by shufangxun - 4
vision_tower读取不到内容,返回none
#5 opened by caramel678 - 0
Results of Evaluation with MobileVLM_V2-1.7B on GQA/POPE/MME Dataset is Different from that in Paper
#41 opened by ZiangWu-77 - 12
关于手机上运行时间的求教
#13 opened by JennieGao-njust - 0
Interest in training a Phi-3 version?
#48 opened by kinchahoy - 1
MobileVLM_V2-3B doesn't work on llama.cpp ?
#39 opened by weizhou1991 - 0
pre-train dataset
#47 opened by FabienCode - 2
Can MobileVLM v2 receive multiple images at once?
#37 opened by wuwu-C - 0
I'm curious that why MobileLLaMA 2.7B is faster then OpenLLaMA reported in v1 paper?
#46 opened by XiaohuJoshua - 5
how to finetune on user's own data
#11 opened by 77h2l - 0
questions about fine tune
#43 opened by Bobby-youngking - 3
CUDA out of memory
#38 opened by qazzombie - 2
有中文的readme没有?两张rtx A4000跑不起来,报错
#32 opened by life2048 - 2
How to use our own dataset to test?
#34 opened by QvQKing - 1
请问推理支持batch跑吗?
#33 opened by LianghuiGuo - 1
请问支持量化推理吗?
#36 opened by LianghuiGuo - 2
A100推理为啥很慢呢?是我Inference姿势不对吗?
#35 opened by LianghuiGuo - 2
mobilevlm_v2 with lora
#30 opened by rangmiao - 2
Problem of Finetune
#31 opened by QvQKing - 3
- 2
Hugging Face demo
#24 opened by merveenoyan - 3
clip部分 ldp 跟 直接编码mlp的时间对比
#23 opened by JennieGao-njust - 5
- 0
Warning about tokenizer
#42 opened by xushilin1 - 11
Repetitive response problem with VLM
#27 opened by Muhammad4hmed - 0
FlashAttention1.0.9 error in 2080Ti
#40 opened by miraclewkf - 2
any lora for stage 2?
#22 opened by shawnricecake - 2
- 2
- 3
Some question on selection device and card
#15 opened by alone4u1314 - 2
Question about mobile platform deploy
#10 opened by JiaoYanMoGu - 3
你们是怎么在骁龙888上运行的?
#8 opened by xsailor511 - 9
how to use lora
#6 opened by liuweixue001 - 4
实现移动端部署的路径
#4 opened by JennieGao-njust - 7
inference on iPhone
#2 opened by tstanek390 - 1
请问支持中文推理/中文数据微调吗?
#20 opened by LianghuiGuo - 1
Does it support Chinese instruction for mobileVLM?
#16 opened by ghoshaw - 6
- 2
- 4
- 4
Benchmark Code
#9 opened by iszhiyang - 3
MobileVLM weights?
#1 opened by pHaeusler