dvlab-research MGM issues

dvlab-research / MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Apache License 2.0

3.22k stars 280 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

为什么输出结果为nan呢

#87 freja-zy closed 7 months ago
1
how to prompt to get short response

#86 GallonDeng opened 7 months ago
2
Some questions about the demo

#85 cyy-1234 opened 7 months ago
3
Huggingface inference script

#84 berry-ding opened 7 months ago
1
Finetune

#83 ZhangScream opened 7 months ago
7
Deployed mini-Gemini in the Windows system and encountered the following error during the “Launch a Graph web server” step.Seeking help to resolve the issue

#82 ghost opened 7 months ago
2
Deployed mini-Gemini in the Windows system and encountered the following error during the ”Launch a Graph web server“ step. seeking help from a skilled user to resolve the issue

#81 ghost closed 7 months ago
1
Updated the Readme file and make it more brief

#80 Dopplenum opened 7 months ago
0
Can this model do graph prediction tasks? For example, predict the future trend of personal social graph.

#79 brainplait opened 7 months ago
1
About the idea to further enhance the performance.

#78 lucasjinreal opened 7 months ago
4
加载模型时卡住了

#77 kimi360 closed 6 months ago
3
请问为什么在执行”python -m minigemini.serve.controller --host 0.0.0.0 --port 10000“时会出现 404 Not Found

#76 liuwenxin0410 opened 7 months ago
11
为啥我6张4090 24G,微调Mini-Gemini-8x7B会显存不够QAQ

#75 HongLouyemeng closed 7 months ago
4
ModuleNotFoundError: No module named 'open_clip'

#74 XHB-ZMM closed 7 months ago
1
local variable 'data_dict' referenced before assignment 这个问题是有同学碰到过吗

#73 HongLouyemeng closed 7 months ago
1
Inquery about simple request

#72 madhatter349 opened 7 months ago
2
Inquery about the missing images from ocr_vqa, sam, gpt4v-dataset and ALLaVA-4V

#71 patrick-tssn opened 7 months ago
0
button and menu clickdown does not work

#70 jeevikasirwani opened 7 months ago
0
add autoscroll

#69 jeevikasirwani opened 7 months ago
0
raise ValueError(f'Not find vision tower: {vision_tower}')

#68 freja-zy opened 7 months ago
4
如何调用api

#67 RoronoaZoroh closed 7 months ago
1
fix bug when using batch size 1

#66 xylcbd closed 7 months ago
2
部署成功试了后，有时会循环输出，还有对中文不是很友好

#65 chenhaoqiang opened 7 months ago
4
Fixed multiple typos in README.md file

#64 Hunaid2000 closed 3 months ago
0
You are using a model of type mini_gemini_mixtral to instantiate a model of type mini_gemini. This is not supported for all configurations of models and can yield errors.

#63 lightmatmul opened 7 months ago
1
Update train.py

#62 lightmatmul closed 7 months ago
0
Re-opening issue: Mini-Gemini Model Fine-Tuning Anomaly

#61 lightmatmul closed 7 months ago
4
LMDeploy is gonna support the inference of MiniGemini :rocket:

#60 AllentDan closed 7 months ago
1
Failed to continous sft for yi-34B with 8x CUDA graphics card! (deepspeed zero3)

#59 xylcbd closed 7 months ago
2
For multi image

#58 ZhangScream closed 7 months ago
2
关于eval的小问题

#57 liuwenhaha opened 7 months ago
1
Regarding license for using the models

#56 thiner closed 7 months ago
1
minigemini.model.multimodal_encoder.openclip_encoder.CLIP() got NoneType

#55 SuSung-boy closed 7 months ago
1
demo page not working

#54 GallonDeng closed 7 months ago
1
API service support like vllm or sglang?

#53 xiechengmude closed 7 months ago
1
Feature Request: llama.cpp support

#52 deutschthomas closed 7 months ago
1
About vl model path

#51 AllentDan closed 7 months ago
2
minigemini_instruction.json包含了预训练的LLaVA Images，但是在readme中没有写到微调用到了这部分数据

#50 shidingz closed 7 months ago
1
Continue FT from stage 2 with custom data

#49 adrielkuek closed 7 months ago
2
Questions about how to enlarge the base vision tower input resolution

#48 lucasjinreal opened 7 months ago
3
运行代码报错AttributeError: 'list' object has no attribute 'to'， image_aux_features_raw = self.get_model().get_vision_tower_aux()(images_aux).to(dtype=image_features.dtype, device=image_features.device)

#47 shidingz closed 7 months ago
3
Questions about change ViT to 378 input resolution, but got poor results.

#46 OpenJarvisAI opened 7 months ago
5
怎么从你们的检查点启动呢

#45 HongLouyemeng closed 7 months ago
17
How many SAM images were used from ShareGPT4v?

#44 OpenJarvisAI opened 7 months ago
2
关于代码实现的疑问

#43 hhaAndroid closed 7 months ago
5
loss suddenly drop to 0 and remain 0

#42 huxian0402 closed 7 months ago
2
batching giving weird outputs

#41 mukundkhanna123 opened 7 months ago
0
RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [1, 1, 3, 336, 336]

#40 plf1996 closed 7 months ago
3
AttributeError: 'MiniGeminiLlamaModel' object has no attribute 'vlm_uni_query_projector'

#39 tanguozhu closed 7 months ago
0
How to get 13K generation-related instructions dataset?

#38 Xiaolong-RRL closed 7 months ago
3

Previous Next