microsoft LLaVA-Med issues

microsoft / LLaVA-Med

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

Other

1.28k stars 147 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Trainable parameters during finetuning for medical VQA

#81 DopamineLcy opened 2 weeks ago
0
How were conversation metrics calculated in the new Benchmark tests with LLaVA 1.5?

#80 NicoZenith opened 3 weeks ago
0
How to download the images?

#79 zihui-debug opened 1 month ago
9
The "llava/data/download_images.py" file is lost?

#78 BoyCO3 opened 1 month ago
2
Add LLaVA-Med-v1.5.

#77 ChunyuanLI closed 1 month ago
0
CLIPVisionTower'object has no attribute 'device'

#75 2927803072 opened 1 month ago
0
Scripts for evaluations on biomed tasks

#74 rthapa84 opened 1 month ago
0
Results of MMBench-dev

#73 Yanllan opened 1 month ago
0
How to use llava-v1.6-mistral-7b training

#72 xuzhaoyang-svg opened 1 month ago
2
Applying for link to image zip

#71 BUAADreamer closed 1 month ago
1
Regarding the training speed for Medical Visual Instruction Tuning.

#70 xxxstrygs33 opened 2 months ago
0
question about the --version parameter

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

#68 james20141606 opened 2 months ago
0
support llama 2 llama1 EOL

#67 idan-tankel opened 2 months ago
0
About the four delta checkpoints

#66 MandyChaseHappy closed 1 month ago
0
Possible Access to LlaVa-Med using BioMed CLIP?

#65 tj-zhu opened 2 months ago
0
llava/eval/model_vqa.py results incorrectly during inference

#64 veinhao opened 2 months ago
0
Evaluation command -- Parameter file path

#63 hylq66 opened 2 months ago
0
please add huggingface integration

#62 dirtycomputer opened 2 months ago
1
如何进行多机多卡训练？

#61 pengjianqiang opened 2 months ago
0
Problem when downloading PMC articals.

#60 Kingofolk opened 2 months ago
0
How to run VQA inference on a single image?

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

#58 tsungjung411 opened 3 months ago
0
Question about the collection of "Instruction-following data"

#57 CinKKKyo opened 3 months ago
0
How to get "pretrain_mm_mlp_adapter" weights, which are aligned on medical concepts?

#56 nourheshamshaheen opened 3 months ago
0
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 3 months ago
0
What and where is the Loss function used in LLAVA-MED

#54 peterphancong opened 3 months ago
0
Response in messy encoding for RAD-VQA evaluation

#53 YatingPan closed 3 months ago
2
Where we can get the data used in the first stage of training like pubmed_600k.json?

#52 mao1207 opened 3 months ago
0
when use "microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224" , shape mismatch error

#51 jzssz closed 3 months ago
1
How to load LLaVA-Med by LlavaForConditionalGeneration?

#50 WenxiongLiao opened 4 months ago
1
Where can I download the pre-train weights?

#49 YangQiuEric opened 4 months ago
0
Instruct image loss

#48 laihaoran opened 4 months ago
1
one question about the image data

#47 ghost closed 4 months ago
1
the bug in /llava/serve/gradio_patch.py

#46 pqpq17 opened 5 months ago
3
Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory

#45 narminGhaffari opened 5 months ago
2
RuntimeError: probability tensor contains either inf, nan or element < 0

#44 yihp opened 5 months ago
9
out of memory - even reduced the elements in the instruction following dataset to just one

#43 mao1207 opened 5 months ago
2
Removing Dependency on "flash-attn" in a Deep Learning Project

#42 LiangXin1001 opened 5 months ago
2
NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.

#41 yihp opened 5 months ago
3
Bump gradio from 3.23 to 4.11.0

#40 dependabot[bot] opened 6 months ago
1
A sincere request for the annotation files

#39 WindMarx opened 6 months ago
0
support multiprocessing and pmc file removal to save disk space

#38 tgisaturday closed 2 months ago
0
Is it possible to fine-tune for downstream task on a XEON CPU?

#37 tsantra opened 6 months ago
0
So...has anyone actually managed to get this running with results similar to the original paper?

#36 abhisuri97 opened 6 months ago
2
fix closed accuracy calculation

#35 HanwenXuTHU closed 6 months ago
0
Projector weight for model

#34 TrungQuocNguyen opened 6 months ago
1
Evaluation images not in llava_med_image_urls.jsonl?

#33 remvanthull opened 7 months ago
4
A bug about saving model

#32 WindMarx opened 7 months ago
2
downloading datas is very low...

#31 zhoucz97 closed 2 months ago
17