Lightning-AI / Lightning-AI/litgpt
LIMA multiturn dialogues not working correctly?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.7k
- Forks
- 1.5k
- Avg merge
- 15h 37m
- Merged PRs (30d)
- 1
Description
It was stated to use the follow up questions in the multi turn dialogues for LIMA, you would have to set `--data.include_multiturn_conversations True`. I included that and compared it with the original data. It seems only the first instruction-response pair is selected. The follow up pairs are not included in the generated json.
steps to reproduce the dataset creation
```py
def format_dataset(dataset_partition: dict, include_multi_turn_conversations: bool) -> List[dict]:
formatted_ds = []
for entry in dataset_partition:
convo = entry["conversations"]
if include_multi_turn_conversations:
for i in range(0, len(convo) - 1, 2):
formatted_ds.append({"instruction": convo[i], "input": "", "output": convo[i + 1]})
else:
formatted_ds.append({"instruction": convo[0], "input": "", "output": convo[1]})
return formatted_ds
lima=load_dataset('GAIR/lima',token=)
formatted_ds = format_dataset(lima['train'], include_multi_turn_conversations=True)
with open('new_lima_ds.json', 'w') as f:
json.dump(formatted_ds, f,indent=4)
```
you can find the generated file here-[new_lima_ds.json](https://github.com/user-attachments/files/15899084/new_lima_ds.json).
i am curious to know if the `--data.include_multiturn_conversations True` actually works and the expected output because i don't think it includes the follow up response-pairs.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the dataset-formatting entry point controlled by `--data.include_multiturn_conversations`, then compare its generated JSON with the LIMA conversation structure shown in the reproduction. Verify whether every follow-up instruction-response pair is emitted when the flag is enabled, and add or update coverage for that behavior if the repository has a relevant test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100