Commit
•
8a7481d
1
Parent(s):
eefa152
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,18 @@
|
|
| 1 |
-
Update:
|
|
|
|
|
|
|
|
|
|
| 2 |
Cuda info (use this one):
|
| 3 |
Command:
|
|
|
|
| 4 |
CUDA_VISIBLE_DEVICES=0 python llama.py ./models/chavinlo-gpt4-x-alpaca
|
|
|
|
| 5 |
--wbits 4
|
|
|
|
| 6 |
--true-sequential
|
|
|
|
| 7 |
--groupsize 128
|
|
|
|
| 8 |
--save gpt-x-alpaca-13b-native-4bit-128g-cuda.pt
|
| 9 |
|
| 10 |
|
|
|
|
| 1 |
+
Update:
|
| 2 |
+
|
| 3 |
+
Okay... Two different models now. One generated in the Triton branch, one generated in Cuda. Use the Cuda one for now unless the Triton branch becomes widely used.
|
| 4 |
+
|
| 5 |
Cuda info (use this one):
|
| 6 |
Command:
|
| 7 |
+
|
| 8 |
CUDA_VISIBLE_DEVICES=0 python llama.py ./models/chavinlo-gpt4-x-alpaca
|
| 9 |
+
|
| 10 |
--wbits 4
|
| 11 |
+
|
| 12 |
--true-sequential
|
| 13 |
+
|
| 14 |
--groupsize 128
|
| 15 |
+
|
| 16 |
--save gpt-x-alpaca-13b-native-4bit-128g-cuda.pt
|
| 17 |
|
| 18 |
|