Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
|
4 |
---
|
5 |
|
6 |
# Quantization Recipe
|
@@ -42,12 +42,12 @@ torch.save(state_dict, "phi4-mini-8dq4w.pt")
|
|
42 |
|
43 |
We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate the quality of the quantized model.
|
44 |
|
45 |
-
|
46 |
```
|
47 |
lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size 8
|
48 |
```
|
49 |
|
50 |
-
|
51 |
```
|
52 |
import lm_eval
|
53 |
from lm_eval import evaluator
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: mit
|
4 |
---
|
5 |
|
6 |
# Quantization Recipe
|
|
|
42 |
|
43 |
We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate the quality of the quantized model.
|
44 |
|
45 |
+
## baseline
|
46 |
```
|
47 |
lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size 8
|
48 |
```
|
49 |
|
50 |
+
## 8dq4w
|
51 |
```
|
52 |
import lm_eval
|
53 |
from lm_eval import evaluator
|