Update README.md
Browse files
README.md
CHANGED
|
@@ -36,6 +36,8 @@ For the MMLU evaluation, we use a 0-shot CoT setting.
|
|
| 36 |
|
| 37 |
Note：i9 14900、1+13 8ge4 use 4 threads，others use the number of threads that can achieve the maximum speed. All models here have been quantized to q4_0.
|
| 38 |
|
|
|
|
|
|
|
| 39 |
## Model Card
|
| 40 |
|
| 41 |
<div align="center">
|
|
|
|
| 36 |
|
| 37 |
Note：i9 14900、1+13 8ge4 use 4 threads，others use the number of threads that can achieve the maximum speed. All models here have been quantized to q4_0.
|
| 38 |
|
| 39 |
+
You can deploy SmallThinker with offloading support using [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer/tree/main/smallthinker)
|
| 40 |
+
|
| 41 |
## Model Card
|
| 42 |
|
| 43 |
<div align="center">
|