OpenTransformer/sft-data-clean

OpenTransformer SFT Data (Clean) Cleaned and standardized SFT datasets in ShareGPT format for instruction tuning. Format All datasets converted to ShareGPT format: {"conversations": [{"from": "human", "value": "..."}, {"from": "gpt", "value": "..."}]} Files File Source Examples Description dolly-15k-sharegpt.jsonl databricks/dolly-15k 14,867 Human-written instruction data Cleaning Pipeline The sft_cleaner.py script:… See the full description on the dataset page: https://huggingface.co/datasets/OpenTransformer/sft-data-clean.

<iframe src="https://silytics.si/embed/item/2cec9a1d-6e24-4f6e-8238-28724547ff4f" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.