ShareGPT4Omni/ShareGPT4Video issues and pull requests

#47 - Code License

Issue - State: open - Opened by waybarrios about 1 month ago

#46 - lack CLIPVIT

Issue - State: open - Opened by zzk6626 about 2 months ago

#45 - [Bug]

Issue - State: open - Opened by BornSaint 3 months ago

#44 - [Bug] Pydantic incompatible with latest fastapi

Issue - State: open - Opened by BornSaint 3 months ago

#43 - NotImplementedError: Cannot copy out of meta tensor; no data!

Issue - State: open - Opened by lianhh1212 3 months ago

#42 - incomplete data

Issue - State: open - Opened by dazhangyu123 4 months ago

#41 - Finetuning

Issue - State: open - Opened by spidercatfly 5 months ago - 1 comment

#40 - Enhance Image Resizing Efficiency

Pull Request - State: open - Opened by mandlinsarah 6 months ago

#39 - Enhanced image loading reliability with error handling

Pull Request - State: open - Opened by mandlinsarah 6 months ago

#38 - Frame concatenation methods are different between gradio demo and `fast_captioner_lmdeploy.py`?

Issue - State: open - Opened by Liam-lyr 6 months ago

#37 - Training script?

Issue - State: open - Opened by rrzhang139 6 months ago - 1 comment

#36 - Data Preprocessing

Issue - State: open - Opened by exiawsh 7 months ago

#35 - update

Pull Request - State: open - Opened by Niujunbo2002 7 months ago

#34 - The usage of ShareCaptioner-Video

Issue - State: open - Opened by huangyf530 7 months ago - 1 comment

#33 - The training cost of the ShareCaptioner-Video

Issue - State: open - Opened by ShiYaya 7 months ago

#32 - 拉了一个多模态大模型技术交流群，大家可以加入进来进行技术交流

Issue - State: closed - Opened by feihuamantian 7 months ago

#31 - What are the main differences between ShareGPT 4Video-8B and ShareCaptioner Video

Issue - State: open - Opened by lcc157 7 months ago - 2 comments

#30 - Dataset generated with the ShareCaptioner-Video

Issue - State: open - Opened by rohun-tripathi 7 months ago - 1 comment

#29 - Questions about lmdeploy version and GPU usage

Issue - State: open - Opened by YoungjaeDev 7 months ago - 6 comments

#28 - Which captions were used for the evaluation in Table 7 - Human Preference?

Issue - State: open - Opened by rohun-tripathi 7 months ago

#27 - Where can I find the prompts used for creating the 181K VQA dataset?

Issue - State: open - Opened by YoungjaeDev 7 months ago

#26 - How much VRAM size is required for fast_captioner inference?

Issue - State: open - Opened by WuTao-CS 7 months ago

#25 - Found a typo in Sec4.1

Issue - State: open - Opened by huskydoge 7 months ago

#24 - detail of slide_captioner_lmdeploy.py

Issue - State: open - Opened by meteorlium 7 months ago - 2 comments

#23 - panda video dataset

Issue - State: closed - Opened by Nastu-Ho 8 months ago - 1 comment

#22 - Question about "slide_captioner_lmdeploy.py"

Issue - State: closed - Opened by Joanna0123 8 months ago - 1 comment

#21 - Can you publish the code that uses the key frame extraction part?

Issue - State: closed - Opened by V1ncentDemo 8 months ago - 1 comment

#20 - add fast captioner with lmdeploy

Pull Request - State: closed - Opened by zehuichen123 8 months ago

#19 - Update README.md

Pull Request - State: closed - Opened by Wiselnn570 8 months ago

#18 - Great work! What is the difference between these two models?

Issue - State: closed - Opened by WilTay1 8 months ago - 1 comment

#17 - 153k video instruction data

Issue - State: closed - Opened by Nastu-Ho 8 months ago - 1 comment

#16 - What are the principles behind the selection of baseline models?

Issue - State: closed - Opened by ShiYaya 8 months ago - 1 comment

#15 - "num_frames = 16" in run.py means taking out an average of 16 frames of a video?

Issue - State: closed - Opened by NuyoaHygge 8 months ago - 1 comment

#14 - About VRAM SIZE

Issue - State: closed - Opened by joseph16388 8 months ago - 1 comment

#13 - question about "Batch inference code for captioner"

Issue - State: closed - Opened by zZer0o 8 months ago - 1 comment

#12 - Release for the obtained summary for 40K

Issue - State: closed - Opened by ermu2001 8 months ago - 1 comment

#11 - Do you plan to quantize the model/ reduce the size of the ShareCaptioner-Video model?

Issue - State: open - Opened by radna0 8 months ago - 1 comment

#10 - ValueError: Trying to set a tensor of shape torch.Size([577, 1024]) in "weight" (which has shape torch.Size([257, 1024])), this look incorrect.

Issue - State: closed - Opened by haruka-025 8 months ago - 3 comments

#9 - Data Preprocess pipeline

Issue - State: closed - Opened by jin-qq 8 months ago - 1 comment

#8 - Missing "panda"?

Issue - State: closed - Opened by linzhiqiu 8 months ago - 7 comments

#7 - Download error when trying to download from huggingface

Issue - State: closed - Opened by linzhiqiu 8 months ago - 1 comment

#6 - Demos about ShareCaptioner-Video

Issue - State: closed - Opened by hkunzhe 8 months ago - 2 comments

#5 - Map video_id (pexels/pixabay) back to its original url id

Issue - State: closed - Opened by hkunzhe 8 months ago - 1 comment

#4 - Caption data of ShareGPT4Video dataset

Issue - State: closed - Opened by Marlod390 9 months ago - 1 comment

#3 - Compare with LLaVANext-8B?

Issue - State: open - Opened by mu-cai 9 months ago

#2 - Inference returns null str.

Issue - State: closed - Opened by ChawDoe 9 months ago - 4 comments

#1 - Inference code of sharegpt4video?

Issue - State: closed - Opened by ChawDoe 9 months ago - 1 comment

GitHub / ShareGPT4Omni/ShareGPT4Video issues and pull requests