Skip to content

Issues: dvlab-research/MGM

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

58 Open 73 Closed
58 Open 73 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

article error
#136 opened Sep 22, 2024 by TuuSiwei
Unable to Merge LoRA Weights with Base Model: ValueError: Can't find 'adapter_config.json' at ...
#135 opened Sep 5, 2024 by PARSA-MHMDI
CHAIR Evaluation
#134 opened Jul 28, 2024 by itsqyh
TypeError: MGMllamaForCausalLM.forward() got an unexpected keyword argument 'cache_position'
#133 opened Jul 17, 2024 by czm708033
2
when use stable-diffusion,AttributeError: 'NoneType' object has no attribute 'tokenize'
#131 opened Jul 1, 2024 by ALR-alr
1
llama3 result is repeated many times
#130 opened Jun 19, 2024 by pennypengpm
1
Does MGM support in-context(few-shot) inference?
#129 opened Jun 15, 2024 by waltonfuture
Will there be support for Qwen2?
#128 opened Jun 12, 2024 by huxian0402
How to access hidden states?
#127 opened Jun 11, 2024 by Divyanshsingh1910
1
I get this error: WARNING: tokenization mismatch: 156 vs. 161. (ignored) when I finetune llama3
#126 opened Jun 5, 2024 by shidingz
1
Do you meet the error "MGMConfig"?
#124 opened May 29, 2024 by strawberryrs620
Requirement for pretraining weights of LLaMa-3-8B-Instruct
#121 opened May 25, 2024 by shiwk23
Can provide laion-gpt4v dataset images zip?
#120 opened May 25, 2024 by TuuSiwei
mgm-34b-hd, should have a 'model_type' key in its config.json
#119 opened May 22, 2024 by chrisx599
2
Inference problem about the demo.
#118 opened May 22, 2024 by ApolloRay
1
The data for alignment and finetuning contains duplicates. Can you please explain why this is happening?
#117 opened May 21, 2024 by KANGRuipeng
1
| EORROR | stderr | RecursionError: Maximun recursion depth exceeded in comparison
#115 opened May 13, 2024 by linyf38
1
May I ask if the current inference code does not support multi images input
#114 opened May 12, 2024 by Angelalilyer
1
多轮对话修改图像输入后报错
#113 opened May 11, 2024 by pennypengpm
Generation-related Instructions dataset link
#112 opened May 10, 2024 by berry-ding
1
关于多机多卡效果不如单机多卡好的问题
#111 opened May 9, 2024 by DePengW
1
LLama 70B support
#108 opened May 3, 2024 by PrateekPal641
Inference speed
#107 opened May 3, 2024 by PrateekPal641
lora initialisation missing from builder.py
#106 opened May 2, 2024 by adrielkuek
1
Congratulations for the best LLaVA derived models !
#104 opened Apr 30, 2024 by deepbeepmeep
1
ProTip! Add no:assignee to see everything that’s not assigned.