askmyteapot commited on
Commit
9914282
1 Parent(s): bb3f8f2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
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, perfdamp 0.1
9
- (<i>the default perfdamp 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.
 
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.