liuhaotian commited on
Commit
4ad10fb
1 Parent(s): 4e05835

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -5
app.py CHANGED
@@ -329,11 +329,10 @@ ONLY WORKS WITH GPU!
329
  You can load the model with 8-bit or 4-bit quantization to make it fit in smaller hardwares. Setting the environment variable `bits` to control the quantization.
330
 
331
  Recommended configurations:
332
- | Hardware | Bits |
333
- |--------------------|----------------|
334
- | A10G-Large (24G) | 8 (default) |
335
- | T4-Medium (16G) | 4 |
336
- | A100-Large (40G) | 16 |
337
  """
338
 
339
  tos_markdown = """
 
329
  You can load the model with 8-bit or 4-bit quantization to make it fit in smaller hardwares. Setting the environment variable `bits` to control the quantization.
330
 
331
  Recommended configurations:
332
+ | Hardware | A10G-Large (24G) | T4-Medium (15G) | A100-Large (40G) |
333
+ |-------------------|------------------|-----------------|------------------|
334
+ | **Bits** | 8 (default) | 4 | 16 |
335
+
 
336
  """
337
 
338
  tos_markdown = """