TheYuriLover
commited on
Commit
•
389a670
1
Parent(s):
54579f2
Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,4 @@ This quantization was made by using this repository: https://github.com/qwopqwop
|
|
7 |
|
8 |
And I used the triton branch with all the gptq implementations available (true_sequential + act_order + groupsize 128)
|
9 |
|
10 |
-
CUDA_VISIBLE_DEVICES=0 python llama.py ./chronos-13b-GPTQ-Triton c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors
|
|
|
7 |
|
8 |
And I used the triton branch with all the gptq implementations available (true_sequential + act_order + groupsize 128)
|
9 |
|
10 |
+
CUDA_VISIBLE_DEVICES=0 python llama.py ./chronos-13b-GPTQ-Triton c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors chronos-13b-4bit-128g-ts-ao.safetensors
|