add colab
Browse files
README.md
CHANGED
|
@@ -13,6 +13,9 @@ inference: False
|
|
| 13 |
|
| 14 |
This is [open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b) sharded into 2 GB shards, and in 8-bit precision using `bitsandbytes==0.38.0`. Please refer to the original model card for details.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |
## loading
|
|
|
|
| 13 |
|
| 14 |
This is [open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b) sharded into 2 GB shards, and in 8-bit precision using `bitsandbytes==0.38.0`. Please refer to the original model card for details.
|
| 15 |
|
| 16 |
+
<a href="https://colab.research.google.com/gist/pszemraj/166ad661c6af1e024d4e2897621fc886/open_llama_13b-sharded-8bit-example.ipynb">
|
| 17 |
+
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
| 18 |
+
</a>
|
| 19 |
|
| 20 |
|
| 21 |
## loading
|