Skip to content

Commit 204424f

Browse files
author
yanxinl4
committed
2 parents 1aa33c0 + 7b3f0c9 commit 204424f

File tree

1 file changed

+3
-11
lines changed

1 file changed

+3
-11
lines changed

eval/scripts/README.md

Lines changed: 3 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,5 @@
11
## **Generate LLM code**
22

3-
To run the script, go to the root of this repo and use the following command from the repository root:
4-
5-
```bash
6-
python evaluation/scripts/gencode_json.py [options]
7-
```
8-
93
Your first need to set up your API keys. For this, create a `keys.cfg` file at the root of the repository
104
and add keys as follows:
115

@@ -15,10 +9,10 @@ ANTHROPIC_KEY = 'your_api_key'
159
GOOGLE_KEY = 'your_api_key' 
1610
```
1711

18-
For example, to create model results with `gpt-4o` and the default settings, run
12+
For example, to create model results with `gpt-4o` and the default settings, go to the root of this repo and run
1913

2014
```bash
21-
python evaluation/scripts/gencode_json.py --model gpt-4o
15+
python eval/scripts/gencode_json.py --model gpt-4o
2216
```
2317

2418
### Command-Line Arguments
@@ -36,7 +30,5 @@ Download the [numeric test results](https://drive.google.com/drive/folders/1W5GZ
3630
To run the script, go to the root of this repo and use the following command:
3731

3832
```bash
39-
python evaluation/scripts/test_generated_code.py
33+
python eval/scripts/test_generated_code.py --model "model_name"
4034
```
41-
42-
Please edit the `test_generated_code.py` source file to specify your model name, results directory and problem set (if not `problems_all.jsonl`).

0 commit comments

Comments
 (0)