Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,10 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
-
QuicktypeGPT is an on-device C-written large language model (LLM) to assist you typing quicker and carrying out meaningful conversations
|
5 |
|
6 |
-
This model only has 15M parameters (dim = 288, 6 layers, 6 heads and 6 kv heads) and 27MB. The model is pre-trained on a single A40 GPU and can be inferenced through a pure C program on a laptop CPU (e.g. AMD, Intel) with decent quality and speed. This project is to demonstrate that
|
|
|
|
|
7 |
|
8 |
For more details, please refer to [quicktypeGPT](https://github.com/chaoluond/quicktypeGPT) github project.
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
**QuicktypeGPT is an on-device C-written large language model (LLM) to assist you typing quicker and carrying out meaningful conversations.**
|
5 |
|
6 |
+
This model only has 15M parameters (dim = 288, 6 layers, 6 heads and 6 kv heads) and 27MB. The model is pre-trained on a single A40 GPU and can be inferenced through a pure C program on a laptop CPU (e.g. AMD, Intel) with decent quality and speed. This project is to demonstrate that:
|
7 |
+
- We do not need to train a very sophisticated LLM but can still achieve santisfactory performance if the LLM is only focused on a small and dedicated domain or task.
|
8 |
+
- We can deploy small LLMs on edge devices (e.g. desktop, laptop, tablet or phone) to perform inference tasks without relying on the servers in the cloud.
|
9 |
|
10 |
For more details, please refer to [quicktypeGPT](https://github.com/chaoluond/quicktypeGPT) github project.
|