Merge pull request #235 from msinha251/Fixing-data-readme

This commit is contained in:
Wing Lian
2023-06-23 13:52:01 -04:00
committed by GitHub

View File

@@ -10,10 +10,10 @@ curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarit
## Convert the JSON data files to JSONL.
```shell
python3 ./scripts/alpaca_json_to_jsonl.py --input data/alpaca_data_gpt4.json > data/alpaca_data_gpt4.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/vicuna_cleaned.json > data/vicuna_cleaned.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/roleplay-similarity_0.6-instruct-dataset.json > data/roleplay-similarity_0.6-instruct-dataset.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --input data/raw/gpt4-instruct-similarity-0.6-dataset.json > data/gpt4-instruct-similarity-0.6-dataset.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --file data/alpaca_data_gpt4.json --output data/alpaca_data_gpt4.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/vicuna_cleaned.json --output data/vicuna_cleaned.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/roleplay-similarity_0.6-instruct-dataset.json --output data/roleplay-similarity_0.6-instruct-dataset.jsonl
python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/gpt4-instruct-similarity-0.6-dataset.json --output data/gpt4-instruct-similarity-0.6-dataset.jsonl
```
---