Comments (2)
Hi, thanks for your interest in our work and also congrats to your great work!
But we do not think the comparisons are essential at this version, there are two reasons.
- We don’t think the core idea and design are highly similar to your work. In Mini-Gemini, HR is used to provide candidates only and used to provide the key and value, which is quite different from your work. Dual pathways is widely-used things in CV, so we donot view it neither declare it as a total novelty in our work. Moreover, HR is only one point in Mini-Gemini.
- We view these two works as concurrent work, and the released date only has about two weeks. Because LLaVA-HR is released at 03/05, and we already finished all validation experiments and also start the method writing at that time. So, we don’t view it as the previous work and not include it for discussion.
Of course, in the future work or next version, we will compare with your work with further discussion.
from mgm.
Thank you! We sincerely wish you good luck !
from mgm.
Related Issues (20)
- | EORROR | stderr | RecursionError: Maximun recursion depth exceeded in comparison HOT 1
- dataset miss problem HOT 1
- The data for alignment and finetuning contains duplicates. Can you please explain why this is happening? HOT 1
- Inference problem about the demo. HOT 1
- mgm-34b-hd, should have a 'model_type' key in its config.json HOT 2
- Can provide laion-gpt4v dataset images zip?
- Requirement for pretraining weights of LLaMa-3-8B-Instruct
- error in loading
- loss 0 and grad nan HOT 3
- Do you meet the error "MGMConfig"?
- 使用多gpu启动worker,对话时报错 HOT 1
- I get this error: WARNING: tokenization mismatch: 156 vs. 161. (ignored) when I finetune llama3 HOT 1
- How to access hidden states? HOT 1
- Will there be support for Qwen2?
- Does MGM support in-context(few-shot) inference?
- llama3 result is repeated many times HOT 1
- when use stable-diffusion,AttributeError: 'NoneType' object has no attribute 'tokenize' HOT 1
- ImportError: cannot import name 'packaging' from 'pkg_resources' HOT 1
- TypeError: MGMllamaForCausalLM.forward() got an unexpected keyword argument 'cache_position' HOT 1
- CHAIR Evaluation
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mgm.