Commit
•
388d851
1
Parent(s):
e41c962
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
GPTQ 4bit quantization of: https://huggingface.co/chavinlo/gpt4-x-alpaca
|
| 2 |
+
|
| 3 |
+
Command:
|
| 4 |
+
CUDA_VISIBLE_DEVICES=0 python llama.py ./models/chavinlo-gpt4-x-alpaca
|
| 5 |
+
--wbits 4
|
| 6 |
+
--true-sequential
|
| 7 |
+
--act-order
|
| 8 |
+
--groupsize 128
|
| 9 |
+
--save gpt-x-alpaca-13b-native-4bit-128g.pt
|