askmyteapot
commited on
Commit
•
9914282
1
Parent(s):
bb3f8f2
Update README.md
Browse files
README.md
CHANGED
@@ -5,8 +5,8 @@
|
|
5 |
# My secret sauce:
|
6 |
* Using comit <a href="https://github.com/0cc4m/GPTQ-for-LLaMa/tree/3c16fd9c7946ebe85df8d951cb742adbc1966ec7">3c16fd9</a> of 0cc4m's GPTQ fork
|
7 |
* Using PTB as the calibration dataset
|
8 |
-
* Act-order, True-sequential,
|
9 |
-
(<i>the default
|
10 |
* No groupsize
|
11 |
* Will run with CUDA, does not need triton.
|
12 |
* Quant completed on a 'Premium GPU' and 'High Memory' Google Colab.
|
|
|
5 |
# My secret sauce:
|
6 |
* Using comit <a href="https://github.com/0cc4m/GPTQ-for-LLaMa/tree/3c16fd9c7946ebe85df8d951cb742adbc1966ec7">3c16fd9</a> of 0cc4m's GPTQ fork
|
7 |
* Using PTB as the calibration dataset
|
8 |
+
* Act-order, True-sequential, percdamp 0.1
|
9 |
+
(<i>the default percdamp is 0.01</i>)
|
10 |
* No groupsize
|
11 |
* Will run with CUDA, does not need triton.
|
12 |
* Quant completed on a 'Premium GPU' and 'High Memory' Google Colab.
|