Commit
·
9bdb4c9
1
Parent(s):
6a40aa9
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,8 +12,10 @@ pipeline_tag: text-generation
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Attention
|
|
|
|
| 15 |
This model is the same as [cerebras/Cerebras-GPT-13B](https://huggingface.co/cerebras/Cerebras-GPT-13B), but the checkpoints were resharded so
|
| 16 |
that each checkpoint has a maximum size of 1GB. This makes the loading process easier on low-resource environments, such as Google Colab.
|
|
|
|
| 17 |
|
| 18 |
# Cerebras-GPT 13B
|
| 19 |
Check out our [Blog Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Attention
|
| 15 |
+
<span style="color:red">
|
| 16 |
This model is the same as [cerebras/Cerebras-GPT-13B](https://huggingface.co/cerebras/Cerebras-GPT-13B), but the checkpoints were resharded so
|
| 17 |
that each checkpoint has a maximum size of 1GB. This makes the loading process easier on low-resource environments, such as Google Colab.
|
| 18 |
+
</span>
|
| 19 |
|
| 20 |
# Cerebras-GPT 13B
|
| 21 |
Check out our [Blog Post](https://www.cerebras.net/cerebras-gpt) and [arXiv paper](https://arxiv.org/abs/2304.03208)!
|