Spaces:
Running
on
A100
Running
on
A100
MekkCyber
commited on
Commit
·
d3bbedc
1
Parent(s):
4d833a2
improving steps
Browse files
app.py
CHANGED
|
@@ -160,13 +160,15 @@ with gr.Blocks(theme=gr.themes.Soft()) as app:
|
|
| 160 |
gr.Markdown(
|
| 161 |
"""
|
| 162 |
## Instructions
|
| 163 |
-
1.
|
| 164 |
-
2.
|
| 165 |
-
3.
|
| 166 |
-
4.
|
| 167 |
-
5.
|
|
|
|
|
|
|
| 168 |
|
| 169 |
-
Note: This process may take some time depending on the model size and your hardware
|
| 170 |
"""
|
| 171 |
)
|
| 172 |
|
|
|
|
| 160 |
gr.Markdown(
|
| 161 |
"""
|
| 162 |
## Instructions
|
| 163 |
+
1. Login to your HuggingFace account
|
| 164 |
+
2. Enter the name of the Hugging Face model you want to quantize (Make sure you have access to it)
|
| 165 |
+
3. Choose the quantization type.
|
| 166 |
+
4. Optionally, specify the group size.
|
| 167 |
+
5. Optionally, choose a custom name for the quantized model
|
| 168 |
+
6. Click "Quantize and Save Model" to start the process.
|
| 169 |
+
7. Once complete, you'll receive a link to the quantized model on Hugging Face.
|
| 170 |
|
| 171 |
+
Note: This process may take some time depending on the model size and your hardware you can check the container logs to see where are you at in the process!
|
| 172 |
"""
|
| 173 |
)
|
| 174 |
|