Auto Sync from git://github.com/01-ai/Yi.git/commit/5ed73fe931e7b95ad6dbd4d8091cd21b199d9bbb
This commit is contained in:
36
README.md
36
README.md
@@ -87,7 +87,7 @@ pipeline_tag: text-generation
|
|||||||
- [Models](#models)
|
- [Models](#models)
|
||||||
- [Chat models](#chat-models)
|
- [Chat models](#chat-models)
|
||||||
- [Base models](#base-models)
|
- [Base models](#base-models)
|
||||||
- [Other info](#other-info)
|
- [Model info](#model-info)
|
||||||
- [News](#news)
|
- [News](#news)
|
||||||
- [How to use Yi?](#how-to-use-yi)
|
- [How to use Yi?](#how-to-use-yi)
|
||||||
- [Quick start](#quick-start)
|
- [Quick start](#quick-start)
|
||||||
@@ -276,11 +276,35 @@ Yi-6B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K)
|
|||||||
|
|
||||||
- For chat and base models
|
- For chat and base models
|
||||||
|
|
||||||
Model | Intro | Default context window | Pretrained tokens | Training Data Date
|
<table>
|
||||||
|---|---|---|---|---
|
<thead>
|
||||||
6B series models |They are suitable for personal and academic use. | 4K | 3T | Up to June 2023
|
<tr>
|
||||||
9B model| It is the best at coding and math in the Yi series models.|4K | Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. | Up to June 2023
|
<th>Model</th>
|
||||||
34B series models | They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.|4K | 3T | Up to June 2023
|
<th>Intro</th>
|
||||||
|
<th>Default context window</th>
|
||||||
|
<th>Pretrained tokens</th>
|
||||||
|
<th>Training Data Date</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody><tr>
|
||||||
|
<td>6B series models</td>
|
||||||
|
<td>They are suitable for personal and academic use.</td>
|
||||||
|
<td rowspan="3">4K</td>
|
||||||
|
<td>3T</td>
|
||||||
|
<td rowspan="3">Up to June 2023</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>9B series models</td>
|
||||||
|
<td>It is the best at coding and math in the Yi series models.</td>
|
||||||
|
<td>Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens.</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>34B series models</td>
|
||||||
|
<td>They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.</td>
|
||||||
|
<td>3T</td>
|
||||||
|
</tr>
|
||||||
|
</tbody></table>
|
||||||
|
|
||||||
|
|
||||||
- For chat models
|
- For chat models
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user