Comments (2)
I start with Pythia-1.4B/GPT-3 XL's model
config.
I reduce the head dim from 128 to 64. (I believe this is a safe step because: 1. Falcon does that. https://huggingface.co/tiiuae/falcon-7b . 2. If you look at the GPT-3 family's shape, the GPT3-2.7B used an even smaller head dim compared with GPT-3 XL.
We use GQA and set the number of query groups to 4.
In order to fit the model with 16K per-GPU-batch size, we reduced the number of layers from 24 to 22. Larger batch size leads to higher MFU /throughput. Because at the end of the day, your x-axis is the money you used to train a model, and your y-axis is the model's performance/the impact you made.
from tinyllama.
Thanks for your clarification. Is there any comparison between different number of query groups for 1b models like inference speed and accuracy?
from tinyllama.
Related Issues (20)
- On the visualization of Wandb in fine-tuning
- Is there any simple demo of fine-tuning TinyLlama HOT 4
- More intermediate checkpoints in < 240k steps
- The results under the FastChat framework are quite bizarre?
- 模型和代码欢迎发布到wisemodel.cn开源社区
- Encountered an issue while loading the model using transformers HOT 1
- A potential bug in multi-GPU training HOT 1
- Where is the pretraing example of llama-1.1b-chat
- Would it be possible to provide help with evaluation?
- On which will it run better
- Training Run - New Tokenizer HOT 1
- Llama 3 HOT 2
- model结构 HOT 1
- model.py HOT 1
- Clarify Chinese support or not on README HOT 1
- 有没有chat模型的其余benchmark的报道,例如mt-bench?
- lightning run model HOT 1
- For pretraining, does it inlcude Block Causal Attention and Block Diagonal Mask?
- 你好,我想问下TinyLlama进行指令微调的代码有吗?以及微调的template格式是什么样呢? HOT 1
- torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 请问你使用的是哪个版本的torch?我用的2.1.0 2.3.1 2.4的都报这个错
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 tinyllama.