Update app.py
Browse files
app.py
CHANGED
@@ -233,6 +233,9 @@ with gr.Blocks(theme='NoCrypt/miku') as demo:
|
|
233 |
We also found the following resources helpful:
|
234 |
[How does GPT-3 spend its 175B parameters?](https://www.lesswrong.com/posts/3duR8CrvcHywrnhLo/how-does-gpt-3-spend-its-175b-parameters)
|
235 |
and [LLM Parameter Counting](https://kipp.ly/transformer-param-count/).
|
|
|
|
|
|
|
236 |
## How To Use
|
237 |
Simply input the model details, such as the hidden size, number of layers, and attention heads, and press 'Calculate Parameters' to get a result.
|
238 |
""")
|
|
|
233 |
We also found the following resources helpful:
|
234 |
[How does GPT-3 spend its 175B parameters?](https://www.lesswrong.com/posts/3duR8CrvcHywrnhLo/how-does-gpt-3-spend-its-175b-parameters)
|
235 |
and [LLM Parameter Counting](https://kipp.ly/transformer-param-count/).
|
236 |
+
|
237 |
+
Note that this exists for `.safetensor` files in the explorer.
|
238 |
+
|
239 |
## How To Use
|
240 |
Simply input the model details, such as the hidden size, number of layers, and attention heads, and press 'Calculate Parameters' to get a result.
|
241 |
""")
|