Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,12 @@
|
|
| 1 |
<div align="center">
|
| 2 |
|
| 3 |
# TinyLlama-1.1B
|
| 4 |
-
English | [δΈζ](README_zh-CN.md)
|
| 5 |
</div>
|
| 6 |
|
| 7 |
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs ππ. The training has started on 2023-09-01.
|
| 8 |
|
| 9 |
<div align="center">
|
| 10 |
-
<img src="
|
| 11 |
</div>
|
| 12 |
|
| 13 |
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
|
|
|
|
| 1 |
<div align="center">
|
| 2 |
|
| 3 |
# TinyLlama-1.1B
|
|
|
|
| 4 |
</div>
|
| 5 |
|
| 6 |
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs ππ. The training has started on 2023-09-01.
|
| 7 |
|
| 8 |
<div align="center">
|
| 9 |
+
<img src="TinyLlama_logo.png" width="300"/>
|
| 10 |
</div>
|
| 11 |
|
| 12 |
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
|