Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix table syntax #2204

Merged
merged 4 commits into from
Aug 10, 2022
Merged

fix table syntax #2204

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7527c33
fix table syntax
kamalkraj Aug 9, 2022
8d79ba8
Merge branch 'master' into patch-2
conglongli Aug 10, 2022
c01cae7
Merge branch 'master' into patch-2
tjruwase Aug 10, 2022
3718e4b
Merge branch 'master' into patch-2
tjruwase Aug 10, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/_tutorials/model-compression.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,8 +69,8 @@ Apart from the above configs, you may also need to modify the data path in the `

Step 4: After distilling the model, one can also choose to further quantize the distilled model by running the script `125M-L10-Int8-test-64gpu-distilled-group48.sh`, which quantizes both the weights and activations of a distilled model with INT8 quantizer (the weight and activation quantization are introduced in the following sections). note that you need to set the `-reset-iteration` flag when performing the quantization. We provide the zero-shot perplexity result from WikiText-2 and LAMBADA in the following table.

| ---: | ---: | ---: | ---: |
| **GPT (125M)** | **#Layers** | **wikitex2 perplexity** | **LAMBADA** |
| ---------- |---------- |---------- |---------- |
| Uncompressed | 12 | 29.6 | 39.5 |
| Quantization only | 12 | 29.8 | 39.7 |
| Distillation only | 10 | 31.9 | 39.2 |
Expand Down