ethzanalytics
/

gpt-j-6B-8bit-sharded

Text Generation

8-bit precision

Model card Files Files and versions Community

pszemraj commited on Sep 16, 2022

Commit

f94dc64

•

1 Parent(s): 2e8d599

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ inference: False
 This is a version of `hivemind/gpt-j-6B-8bit` for low-RAM loading, i.e., free Colab runtimes :)
-- shards are > 1000MB each
 - a demo notebook of how to use it [is here](https://colab.research.google.com/gist/pszemraj/1c0b32173df5b1efbdb7a2358ed4195b/generate-text-with-an-llm-sharded-on-huggingface.ipynb)

 This is a version of `hivemind/gpt-j-6B-8bit` for low-RAM loading, i.e., free Colab runtimes :)
+- shards are <= 1000MB each
 - a demo notebook of how to use it [is here](https://colab.research.google.com/gist/pszemraj/1c0b32173df5b1efbdb7a2358ed4195b/generate-text-with-an-llm-sharded-on-huggingface.ipynb)