Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,3 +15,10 @@ Instructions:
|
|
| 15 |
- This Space installs torch at runtime before importing TinyLLaVA to avoid build-time failures.
|
| 16 |
- Model used: bczhou/TinyLLaVA-1.5B (CPU-friendly). Change MODEL_PATH in app.py if you have more resources.
|
| 17 |
- Upload an image or enter an image URL, enter an optional prompt, then click Generate.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
- This Space installs torch at runtime before importing TinyLLaVA to avoid build-time failures.
|
| 16 |
- Model used: bczhou/TinyLLaVA-1.5B (CPU-friendly). Change MODEL_PATH in app.py if you have more resources.
|
| 17 |
- Upload an image or enter an image URL, enter an optional prompt, then click Generate.
|
| 18 |
+
|
| 19 |
+
Use this repo in Hugging Face Spaces (CPU). It vendors a minimal tinyllava loader to avoid pip dependency conflicts.
|
| 20 |
+
Startup: set the Space run command to:
|
| 21 |
+
python start.py
|
| 22 |
+
This will install CPU torch at runtime then start app.py.
|
| 23 |
+
|
| 24 |
+
Model: bczhou/TinyLLaVA-1.5B (can be changed in app.py). CPU inference may be slow.
|