Update README.md
Browse files
README.md
CHANGED
@@ -68,7 +68,7 @@ This model was created with [llm-compressor](https://github.com/vllm-project/llm
|
|
68 |
|
69 |
|
70 |
```bash
|
71 |
-
python quantize.py --model_path ibm-granite/granite-3.1-2b-instruct --quant_path "output_dir/granite-3.1-2b-instruct-quantized.w4a16" --calib_size 2048 --dampening_frac 0.01 --observer mse
|
72 |
```
|
73 |
|
74 |
|
@@ -129,6 +129,7 @@ recipe = [
|
|
129 |
scheme="w4a16",
|
130 |
dampening_frac=args.dampening_frac,
|
131 |
observer=args.observer,
|
|
|
132 |
)
|
133 |
]
|
134 |
oneshot(
|
|
|
68 |
|
69 |
|
70 |
```bash
|
71 |
+
python quantize.py --model_path ibm-granite/granite-3.1-2b-instruct --quant_path "output_dir/granite-3.1-2b-instruct-quantized.w4a16" --calib_size 2048 --dampening_frac 0.01 --observer mse --actorder dynamic
|
72 |
```
|
73 |
|
74 |
|
|
|
129 |
scheme="w4a16",
|
130 |
dampening_frac=args.dampening_frac,
|
131 |
observer=args.observer,
|
132 |
+
actorder=args.actorder,
|
133 |
)
|
134 |
]
|
135 |
oneshot(
|