Commit
•
658687b
1
Parent(s):
206e1c7
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
My first quantization uses the quantization method provided by vllm:
|
| 2 |
+
|
| 3 |
+
https://docs.vllm.ai/en/latest/quantization/int8.html
|
| 4 |
+
|
| 5 |
+
NUM_CALIBRATION_SAMPLES = 2048
|
| 6 |
+
|
| 7 |
+
MAX_SEQUENCE_LENGTH = 8192
|
| 8 |
+
|
| 9 |
+
smoothing_strength=0.8
|
| 10 |
+
|
| 11 |
+
I will verify the validity of the model and update the readme as soon as possible.
|