Comments (2)
In fact, the model that has only gone through the pre-training stage can only perform ASR and AAC tasks and is completely incapable of performing any zero-shot tasks. In other words, the problem of task overfitting is even more serious at this point. As you can see in the paper, we introduce a large amount of QA data in the instruction tuning stage, so that the model can see more abundant prompts, thus alleviating the situation of the model not following instructions. However, the model is still struggling to do more difficult tasks, without reducing the lora factor or being activated.
For your second question, I don't quite understand. In pre-training stage and instruction tuning stage, the Q-Former and LoRA are both updated. We used the model after instruction tuning to plot Figure 3. I think the phenomenon your mentioned can only demonstrate that reducing lora scaling to 2.0 is sufficient to activate the model capacity, but does not directly indicate that the pre-trained model can solve these tasks.
from salmonn.
I will close this issue. If you have any question, welcome to reopen it.
from salmonn.
Related Issues (20)
- The role of prompt_pattern parameter HOT 2
- when can we get the codes for trainning? HOT 4
- Adding Code of conduct to repo ! HOT 1
- Adding Contributors section to the readme.md ! HOT 2
- Typo error in README.md
- 什么时候可以得到vicuna7B的模型呢? HOT 1
- 中文能力如何? HOT 2
- How to adopt a speaker verification task? HOT 1
- when can we finetune the model with vicuna7B? HOT 1
- 请问是否在 AAC 任务上和 Qwne-Audio 比较过
- 请问需要下载哪个版本的 whisper-large-v2? HOT 1
- Some questions about this project hoping for your further answers. HOT 2
- config 里面应该再加个 bert config path HOT 1
- 使用 7B 模型,有的时候无法生成 audio caption
- Cannot download Fine-tuned BEATs_iter3+ (AS2M) (cpt2). HOT 2
- SALMONN 7B 使用的Vicuna版本? HOT 1
- 第一阶段speech Qformer的训练和模型 HOT 1
- inference cuda OOM on smaller GPU
- Request for Task Level 3 Training Data
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 salmonn.