Instruction Tuning

Benchmarks

Dataset Name	SOTA Method	Metric
Dolly-15K alpha=5.0	FedHDS	Rouge-L35.79	22	1mo ago
Dolly-15K alpha=0.5	Coreset-Cent	Rouge-L35.48	22	1mo ago
Natural Instructions Meta Non-IID	Coreset-Cent	Rouge-L34.81	22	1mo ago
UNI	ARMADA	RougeL34.53	21	1mo ago
SelfInst	ARMADA	ROUGE-L21.31	21	1mo ago
SNI	ARMADA	RougeL29.63	21	1mo ago
Dolly	LLaMA-3.1-8B	RougeL35.34	21	1mo ago
CoT	ADG	Reasoning Score70.55	20	4d ago
WizardLM	ADG	Reasoning Score75.07	20	4d ago
Alpaca GPT4	ADG	Reasoning75.43	20	4d ago
Instruction Tuning Datasets 1.0 (train test)	K-Center-Greedy	Model Performance1.45	20	1mo ago
Alpaca instruction-tuning 52k	GRADFILTERING	Pairwise Winning Score116	19	1mo ago
IT Evaluation Suite MMLU, BBH, GSM, TydiQA, CodeX, AE	Alpaca-GPT4	MMLU55.7	18	1mo ago
Data Mix	GRADIENTSPACE	Accuracy59.1	16	1mo ago
Vicuna	ARMADA	RougeL Score18.73	11	1mo ago
FLAN subset Average (test)	FedRouter*	ROUGE-156.7	7	16d ago
FLAN All (test)	FedRouter*	ROUGE-157.5	7	16d ago
FLAN Dual (test)	FedRouter*	ROUGE-156.3	7	16d ago
FLAN Single (test)	FedRouter*	ROUGE-156.2	7	16d ago
AlpacaEval 2.0 (test)		Win Rate (LC)11.49	7	1mo ago
Alpaca 52K instruction LLaMA-7B (test)	DQ (2%)	BBH32.9	4	1mo ago
Anthropic HH (test)	SCAR	Win Rate56.3	2	1mo ago
Anthropic HH-RLHF (test)	-	-	0	1mo ago
Dolly-15K	-	-	0	1mo ago

Showing 24 of 24 rows