fix typo in readme (#163)

This commit is contained in:
Deven Mistry
2023-12-20 22:47:41 -05:00
committed by GitHub
parent ce30cc3d8f
commit 3efb1cc2cc

View File

@@ -7,11 +7,11 @@ GPT-4 outputs and clean web text.
Phi-2 efficiently runs on Apple silicon devices with 8GB of memory in 16-bit
precision.
## Setup
## Setup
Download and convert the model:
```sh
```sh
python convert.py
```
@@ -22,7 +22,7 @@ This will make the `weights.npz` file which MLX can read.
> Hugging Face and skip the conversion step.
## Generate
## Generate
To generate text with the default prompt:
@@ -48,7 +48,7 @@ Answer: Logic in mathematics is like a compass in navigation. It helps
To use your own prompt:
```sh
python phi2.py --prompt <your prompt here> --max_tokens <max_tokens_to_generate>
python phi2.py --prompt <your prompt here> --max-tokens <max_tokens_to_generate>
```
To see a list of options run: