Update README.md
Browse files
README.md
CHANGED
@@ -69,12 +69,11 @@ print(code)
|
|
69 |
|
70 |
### Size Comparison
|
71 |
|
72 |
-
```
|
73 |
The table shows comparison VRAM requirements for loading and training
|
74 |
of FP16 Base Model and 4bit GPTQ quantized model with PEFT.
|
75 |
The value for base model referenced from [Model Memory Calculator](https://huggingface.co/docs/accelerate/main/en/usage_guides/model_size_estimator)
|
76 |
from HuggingFace
|
77 |
-
|
78 |
|
79 |
|
80 |
|
|
|
69 |
|
70 |
### Size Comparison
|
71 |
|
|
|
72 |
The table shows comparison VRAM requirements for loading and training
|
73 |
of FP16 Base Model and 4bit GPTQ quantized model with PEFT.
|
74 |
The value for base model referenced from [Model Memory Calculator](https://huggingface.co/docs/accelerate/main/en/usage_guides/model_size_estimator)
|
75 |
from HuggingFace
|
76 |
+
|
77 |
|
78 |
|
79 |
|