Skip to content

Issues: LLaVA-VL/LLaVA-NeXT

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

237 Open 72 Closed
237 Open 72 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Warning: You are using a model of type llava to instantiate a model of type llava_qwen. This is not supported for all configurations of models and can yield errors.
#350 opened Nov 25, 2024 by kydxh
Where is the training script for mid_stage?
#348 opened Nov 22, 2024 by weiwei1206
Big fluctuations in training-loss
#347 opened Nov 22, 2024 by vir-95
LLaVA-Onevision: post_layernorm in SiglipVisionTransformer takes no effect in the forward
#346 opened Nov 22, 2024 by dyou-dev
vision tower not updated after finetune
#345 opened Nov 22, 2024 by wenyuqing
Version of lmms-eval for llava-next image
#344 opened Nov 20, 2024 by EchoDreamer
After the mm_vision_tower and mm_mlp_adapter of llava-onevision-qwen2-7b-ov were fine-tuned, the model parameter shape did not match after the fine-tuning
#342 opened Nov 18, 2024 by zyf8818
4
Can the inference code of LLAVA-OV be modified to support batch inference? Single-instance inference is a bit slow.
#341 opened Nov 18, 2024 by cyinen
Benchmarks of LLAVA-CRITIC
#340 opened Nov 14, 2024 by OctopusXXX
Finetuning LLava NeXT 34B
#339 opened Nov 12, 2024 by akshatbhandari15
Discussion on Setting self.tokenizer.pad_token_id
#338 opened Nov 11, 2024 by nkkbr
lmms-lab vs llava-hf
#337 opened Nov 8, 2024 by amew0
2
visual token attention mask 是causal的吗
#336 opened Nov 8, 2024 by hello-bluedog
Experiments around deleting the last layer of SigLip encoder.
#335 opened Nov 7, 2024 by Natyren
LoRA fine-tuning for llava-video
#334 opened Nov 5, 2024 by H-chenglei
dpo_ov7b.sh训练问题
#333 opened Nov 5, 2024 by zhanghang-official
Docs about llava-critic
#332 opened Nov 5, 2024 by Skyseaee
Input different length of videos for LLaVA-onevision
#331 opened Nov 5, 2024 by zhengrongz
Llama 3 tokenizer is not available. Make sure you have the necessary permissions.
#330 opened Oct 31, 2024 by overwhelmedxh
2
Evaluation of LLaVA-OV with mismatch error
#329 opened Oct 30, 2024 by jiafei1224
1
mDPO support?
#327 opened Oct 29, 2024 by MonolithFoundation
About the llava-ov single-image SFT data noted in single_image.yaml
#326 opened Oct 29, 2024 by SAIS-FUXI
DPO for LLaVa-One-Vision7B？
#325 opened Oct 29, 2024 by Liuziyu77
Why the predict didn't have any image slicing step?
#324 opened Oct 29, 2024 by MonolithFoundation
NotImplementedError: Cannot copy out of meta tensor; no data!
#323 opened Oct 28, 2024 by wuxi-dixi
ProTip! Updated in the last three days: updated:>2024-11-23.