hkust-nlp/deita-quality-scorer-data

Dataset

Dataset Card for Deita Quality Scorer Training Data

3 commits

1 linked in READMEs

updated Jan 16, 2024

See the code

README

Dataset Card for Deita Quality Scorer Training Data

GitHub | Paper

Deita is an open-sourced project designed to facilitate Automatic Data Selection for instruction tuning in Large Language Models (LLMs).

This dataset includes data for training Deita Quality Scorer.

Model Family: Other models and the dataset are found in the Deita Collection

Performance

Model	Align	Data Size	MT-Bench	AlpacaEval(%)	OpenLLM (Avg.)
Proprietary Models
GPT-4-Turbo	?	--	9.32	97.70	--
GPT-4	SFT + PPO	--	8.99	95.03	--
Claude-2	SFT + PPO	--	8.06	91.36	--
GPT-3.5-turbo	SFT + PPO	--	7.94	89.37	--
Open-sourced Models based on LLaMA-1-13B
LIMA	SFT	1K SFT	4.29	41.98	59.82
WizardLM-13B	SFT	70K SFT	6.35	75.31	58.96
Vicuna-13B-v1.3	SFT	125K SFT	6.39	82.11	60.01
Random	SFT	10K SFT	6.03	71.52	60.14
DEITA-LLaMA1-13B-v1.0-sft	SFT	10K SFT	6.60	78.01	64.27
Open-sourced Models based on LLaMA-2-13B
Tulu-2-13B	SFT	326K SFT	6.70	78.90	--
Tulu-2-13B+DPO	SFT + DPO	326K SFT + 60K DPO	7.00	89.50	--
LLaMA2-13B-Chat	SFT + PPO	--	6.65	81.09	--
WizardLM-13B-v1.2	SFT	>70K SFT	7.09	89.17	--
Vicuna-13B-v1.5	SFT	125K SFT	6.57	78.80	61.63
Random	SFT	10K SFT	5.78	65.19	61.32
DEITA-LLaMA2-13B-v1.0-sft	SFT	10K SFT	6.79	81.09	62.71
Open-sourced Models based on Mistral-7B
Mistral-7B-Instruct-v0.1	--	--	6.84	69.65	60.45
Zephyr-7B-sft	SFT	200K SFT	5.32	75.12	60.93
$\text{Zephyr-7B-}\beta$	SFT + DPO	200K SFT + 60K DPO	7.34	90.60	66.36
OpenChat-3.5	C-RLFT	>> 70K C-RLFT	7.81	88.51	--
Starling-7B	C-RLFT + APA	>>70K C-RLFT + 183K APA	8.09	91.99	--
Random	SFT	10K SFT	5.89	56.90	61.72
DEITA-7B-v1.0-sft (6K)	SFT	6K SFT	7.22	80.78	64.94
DEITA-7B-v1.0-sft (10K)	SFT	10K SFT	7.32	81.67	64.00
DEITA-7B-v1.0	SFT + DPO	6K SFT + 10K DPO	7.55	90.06	69.86

Citation

If you find the content of this project helpful, please cite our paper as follows:

@misc{liu2023what,
      title={What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning}, 
      author={Wei Liu and Weihao Zeng and Keqing He and Yong Jiang and Junxian He},
      year={2023},
      eprint={2312.15685},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Contributors

AndrewZeng

3 commits

Similar repos

hkust-nlp/deita-complexity-scorer-data

Dataset

Dataset Card for Deita Complexity Scorer Training Data

hkust-nlp/deita-10k-v0

Dataset

Dataset Card for Deita 10K V0

hkust-nlp/deita-6k-v0

Dataset

Dataset Card for Deita 6K V0

hkust-nlp/deita-quality-scorer

Model

Model Card for Deita Quality Scorer

hkust-nlp/deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

603

hkust-nlp/deita-7B-v1.0

Model

Model Card for Deita 7B V1.0

hkust-nlp/deita-llama2-13b-v1.0-sft

Model

Model Card for Deita Llama2 13B V1.0 SFT

hkust-nlp/deita-7b-v1.0-sft

Model

Model Card for Deita 7B V1.0 SFT

Linked in READMEs

hkust-nlp/deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

603

README badge

hkust-nlp/deita-quality-scorer-data

Dataset

Dataset Card for Deita Quality Scorer Training Data

3 commits

1 linked in READMEs

updated Jan 16, 2024

See the code

README

Dataset Card for Deita Quality Scorer Training Data

GitHub | Paper

Deita is an open-sourced project designed to facilitate Automatic Data Selection for instruction tuning in Large Language Models (LLMs).

This dataset includes data for training Deita Quality Scorer.

Model Family: Other models and the dataset are found in the Deita Collection

Performance

Model	Align	Data Size	MT-Bench	AlpacaEval(%)	OpenLLM (Avg.)
Proprietary Models
GPT-4-Turbo	?	--	9.32	97.70	--
GPT-4	SFT + PPO	--	8.99	95.03	--
Claude-2	SFT + PPO	--	8.06	91.36	--
GPT-3.5-turbo	SFT + PPO	--	7.94	89.37	--
Open-sourced Models based on LLaMA-1-13B
LIMA	SFT	1K SFT	4.29	41.98	59.82
WizardLM-13B	SFT	70K SFT	6.35	75.31	58.96
Vicuna-13B-v1.3	SFT	125K SFT	6.39	82.11	60.01
Random	SFT	10K SFT	6.03	71.52	60.14
DEITA-LLaMA1-13B-v1.0-sft	SFT	10K SFT	6.60	78.01	64.27
Open-sourced Models based on LLaMA-2-13B
Tulu-2-13B	SFT	326K SFT	6.70	78.90	--
Tulu-2-13B+DPO	SFT + DPO	326K SFT + 60K DPO	7.00	89.50	--
LLaMA2-13B-Chat	SFT + PPO	--	6.65	81.09	--
WizardLM-13B-v1.2	SFT	>70K SFT	7.09	89.17	--
Vicuna-13B-v1.5	SFT	125K SFT	6.57	78.80	61.63
Random	SFT	10K SFT	5.78	65.19	61.32
DEITA-LLaMA2-13B-v1.0-sft	SFT	10K SFT	6.79	81.09	62.71
Open-sourced Models based on Mistral-7B
Mistral-7B-Instruct-v0.1	--	--	6.84	69.65	60.45
Zephyr-7B-sft	SFT	200K SFT	5.32	75.12	60.93
$\text{Zephyr-7B-}\beta$	SFT + DPO	200K SFT + 60K DPO	7.34	90.60	66.36
OpenChat-3.5	C-RLFT	>> 70K C-RLFT	7.81	88.51	--
Starling-7B	C-RLFT + APA	>>70K C-RLFT + 183K APA	8.09	91.99	--
Random	SFT	10K SFT	5.89	56.90	61.72
DEITA-7B-v1.0-sft (6K)	SFT	6K SFT	7.22	80.78	64.94
DEITA-7B-v1.0-sft (10K)	SFT	10K SFT	7.32	81.67	64.00
DEITA-7B-v1.0	SFT + DPO	6K SFT + 10K DPO	7.55	90.06	69.86

Citation

If you find the content of this project helpful, please cite our paper as follows:

@misc{liu2023what,
      title={What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning}, 
      author={Wei Liu and Weihao Zeng and Keqing He and Yong Jiang and Junxian He},
      year={2023},
      eprint={2312.15685},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}