Update README.md
Browse files
README.md
CHANGED
@@ -107,6 +107,10 @@ _ = model.generate(**inputs, streamer=streamer, max_new_tokens=200)
|
|
107 |
#Portanto, a área do triângulo equilátero é de 4 centímetros quadrados.
|
108 |
```
|
109 |
|
|
|
|
|
|
|
|
|
110 |
# 4bits
|
111 |
|
112 |
```python
|
|
|
107 |
#Portanto, a área do triângulo equilátero é de 4 centímetros quadrados.
|
108 |
```
|
109 |
|
110 |
+
If you are having a memory problem such as "CUDA Out of memory", you should use 4-bit or 8-bit quantization.
|
111 |
+
For the complete model in colab you will need the A100.
|
112 |
+
If you want to use 4bits or 8bits, T4 or L4 will already solve the problem.
|
113 |
+
|
114 |
# 4bits
|
115 |
|
116 |
```python
|