microsoft LLaVA-Med issues

microsoft / LLaVA-Med

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Other

1.58k stars 201 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Errors are reported using other data sets

#101 jzy-123 opened 1 week ago
0
Error

#100 Huster-Hq opened 4 weeks ago
0
how to get images types from the dataset?

#99 siyan-zhao opened 1 month ago
0
added data/download_images.py

#98 ayyucedemirbas opened 1 month ago
0
ValueError: weight is on the meta device, we need a `value` to put in on 0.

#97 Draculair opened 2 months ago
1
What is the prompt of doing multi-choice questions?

#96 zzzzxciid opened 2 months ago
0
KeyError: 'llava_mistral'

#95 Draculair opened 2 months ago
2
ValueError: weight is on the meta device, we need a `value` to put in on 0.

#94 Mike-ihr opened 2 months ago
0
base model for llava-med-v1.5-mistral-7b

#93 cdxeve opened 2 months ago
0
NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.

#92 quansui398 opened 2 months ago
2
Making it work on CLI

#91 Akshay-Gole closed 3 months ago
0
Why only Gradio?

#90 jogihood opened 3 months ago
0
Update conversation.py

#89 Rickylht opened 3 months ago
0
training hyperparameters of llava-med 1.5

#88 alyakin314 opened 3 months ago
0
Can't we train and fine tune the Llavamed model

#87 liucheny opened 3 months ago
9
Excuse me, I deployed LLaVA-med locally, why is my answer only one word?

#86 ZG-yuan closed 3 months ago
2
biomedical concept alignment data

#85 hddbang opened 4 months ago
1
How can I train this model?

#84 LCR2001 opened 4 months ago
1
About "image.zip" download

#83 NyKxo1 opened 4 months ago
0
How to start a model worker using multiple GPUs？And where is the "--num-gpus"?

#82 WZA-GH opened 4 months ago
1
Trainable parameters during finetuning for medical VQA

#81 DopamineLcy opened 5 months ago
1
How were conversation metrics calculated in the new Benchmark tests with LLaVA 1.5?

#80 NicoZenith opened 5 months ago
0
How to download the images?

#79 zihui-debug opened 6 months ago
10
The "llava/data/download_images.py" file is lost?

#78 BoyCO3 opened 6 months ago
2
Add LLaVA-Med-v1.5.

#77 ChunyuanLI closed 6 months ago
0
CLIPVisionTower'object has no attribute 'device'

#75 2927803072 opened 6 months ago
0
Scripts for evaluations on biomed tasks

#74 rthapa84 opened 6 months ago
0
Results of MMBench-dev

#73 Yanllan opened 6 months ago
0
How to use llava-v1.6-mistral-7b training

#72 xuzhaoyang-svg opened 6 months ago
3
Applying for link to image zip

#71 BUAADreamer closed 6 months ago
3
Regarding the training speed for Medical Visual Instruction Tuning.

#70 xxxstrygs33 opened 7 months ago
0
question about the --version parameter

#69 Yanllan opened 7 months ago
2
where is pubmed_600k.json?

#68 james20141606 opened 7 months ago
2
support llama 2 llama1 EOL

#67 idan-tankel opened 7 months ago
0
About the four delta checkpoints

#66 MandyChaseHappy closed 6 months ago
0
Possible Access to LlaVa-Med using BioMed CLIP?

#65 tj-zhu opened 7 months ago
0
llava/eval/model_vqa.py results incorrectly during inference

#64 veinhao opened 7 months ago
0
Evaluation command -- Parameter file path

#63 hylq66 opened 7 months ago
0
please add huggingface integration

#62 dirtycomputer opened 7 months ago
3
如何进行多机多卡训练？

#61 pengjianqiang opened 7 months ago
0
Problem when downloading PMC articals.

#60 Kingofolk opened 7 months ago
1
How to run VQA inference on a single image?

#59 Raman1121 opened 7 months ago
2
Missing Archive: PMC7236913.tar.gz Not Found on HTTP Server

#58 tsungjung411 opened 8 months ago
0
Question about the collection of "Instruction-following data"

#57 CinKKKyo opened 8 months ago
2
How to get "pretrain_mm_mlp_adapter" weights, which are aligned on medical concepts?

#56 nourheshamshaheen opened 8 months ago
2
使用biomed-clip的llava-med在预训练阶段有用到一般llava使用的web图像-文本对吗？还是只用医学图像-文本预训练

#55 Yang-bug-star opened 8 months ago
0
What and where is the Loss function used in LLAVA-MED

#54 peterphancong opened 8 months ago
0
Response in messy encoding for RAD-VQA evaluation

#53 YatingPan closed 8 months ago
2
Where we can get the data used in the first stage of training like pubmed_600k.json?

#52 mao1207 opened 8 months ago
0
when use "microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224" , shape mismatch error

#51 jzssz closed 8 months ago
1