1 Pull request merged by 1 person

• add multi-image inference

  #67 merged Jun 22, 2024

4 Pull requests opened by 4 people

• Features update

  #65 opened Jun 20, 2024

• Make some ad-hoc changes to use the interleave model

  #73 opened Jun 26, 2024

• Update LLaVA-NeXT.md - Typo (missing letter)

  #75 opened Jun 26, 2024

• Fix prepare inputs labels for multimodal

  #84 opened Jun 28, 2024

12 Issues closed by 7 people

• Will LLaVA-NeXT-interleave 0.5B release?

  #74 closed Jul 2, 2024

• How many A100s used for training?

  #87 closed Jul 2, 2024

• Demo deployment issues

  #85 closed Jul 1, 2024

• Is LLaVA-NeXT-interleave 7B model availble?

  #88 closed Jul 1, 2024

• question about the demo implementation

  #92 closed Jul 1, 2024

• Unable to load interleave model

  #83 closed Jun 29, 2024

• Module Numpy Conflict Error

  #81 closed Jun 28, 2024

• Was CLIP ViT-L/14 Freezed in LLaVA-NeXT-Video-DPO (7B)

  #66 closed Jun 21, 2024

• Missing Parameters While Loading the Checkpoints

  #60 closed Jun 14, 2024

• What is the conv-mode for LLaVA-NeXT-Video-7B-32K

  #54 closed Jun 14, 2024

• No Attribute 'apply_chat_template'

  #51 closed Jun 12, 2024

• How to load the largest models?

  #53 closed Jun 6, 2024

28 Issues opened by 26 people

• When will the training code be available?

  #93 opened Jul 3, 2024

• where is python3 llavavid/eval/eval_activitynet_qa.py?

  #91 opened Jul 1, 2024

• Question regarding multi image inference - import vs demo

  #90 opened Jun 29, 2024

• Question about M4-Instruct datasets

  #89 opened Jun 29, 2024

• SGLang example not working: KeyError: 'answer'

  #86 opened Jun 29, 2024

• Strange Model Loading Issue: Inconsistency with Vision Tower Parameters

  #82 opened Jun 28, 2024

• Issue running llava/eval/model_video_chatgpt_general.py - Missing eval folder

  #80 opened Jun 27, 2024

• LLaVa-NeXT-Video is added to 🤗 Transformers!

  #79 opened Jun 27, 2024

• llama3 chat format error in the example

  #78 opened Jun 27, 2024

• Code of higher-AnyRes

  #77 opened Jun 27, 2024

• ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.

  #76 opened Jun 27, 2024

• About llava-next-interleave inference

  #72 opened Jun 25, 2024

• Actual Demo for Interleave

  #71 opened Jun 24, 2024

• Will the interleaved data opensource?

  #70 opened Jun 24, 2024

• Update the License in the Git Repo

  #69 opened Jun 24, 2024

• The number of tokens occupied by the image encoding

  #68 opened Jun 23, 2024

• Where is the stage 1.5 training confgi?

  #64 opened Jun 17, 2024

• Using llava-next-110b for inference, the return is ['']

  #63 opened Jun 17, 2024

• llavaconfig error

  #62 opened Jun 17, 2024

• Does LLaVA-Next support in-context(few-shot) inference?

  #61 opened Jun 15, 2024

• Question about AnyRes calculations: bug or intended?

  #59 opened Jun 13, 2024

• Inference error of LLaVA-NeXT-Video-7B-DPO

  #58 opened Jun 13, 2024

• Version of ChatGPT 3.5 for evaluation.

  #57 opened Jun 11, 2024

• looking forward releasing training code

  #56 opened Jun 11, 2024

• There is tremendous confusion about which chat templates to use with which models

  #55 opened Jun 7, 2024

• Only output [1, 2] tokens for 'lmms-lab/LLaVA-NeXT-Video-7B-DPO' video demo inference

  #52 opened Jun 5, 2024

• what is the mean of the full model during training?

  #50 opened Jun 5, 2024

• Both demo links are down! Would you please check them out?

  #49 opened Jun 4, 2024

8 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• training code

  #46 commented on Jun 27, 2024 • 6 new comments

• [Question] Is this slated for release in the Transformers library?

  #9 commented on Jun 27, 2024 • 5 new comments

• Training/Finetunning code please

  #41 commented on Jun 25, 2024 • 4 new comments

• 中文ocr效果极差

  #47 commented on Jun 13, 2024 • 3 new comments

• Data to evaluate Video Detailed Description.

  #38 commented on Jun 18, 2024 • 3 new comments

• Will there be supported for llava-hf soon?

  #35 commented on Jun 12, 2024 • 1 new comment

• Video Detailed Description data cannot access if MS account is not from mbzuai

  #31 commented on Jun 18, 2024 • 1 new comment

• When will the training code open sourced?

  #6 commented on Jun 28, 2024 • 1 new comment