tosh

import Jam from 'jam-react';

<Jam roomId="room-id" />
  
  

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
MonarchPipe-7B-slerp	46.12	74.89	66.59	47.49	58.77

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	27.17	±	2.80
		acc_norm	27.17	±	2.80
agieval_logiqa_en	0	acc	39.32	±	1.92

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
pandafish-7b	40	74.23	53.22	40.51	51.99

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	21.65	±	2.59
		acc_norm	21.65	±	2.59
agieval_logiqa_en	0	acc	34.10	±	1.86

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
HeatherSpell-7b	45.65	77.24	75.75	50	62.16

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	28.74	±	2.85
		acc_norm	25.98	±	2.76
agieval_logiqa_en	0	acc	39.63	±	1.92

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
HeatherSpellGen2	40.73	75.43	72.75	47.12	59.01

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	21.65	±	2.59
		acc_norm	20.47	±	2.54
agieval_logiqa_en	0	acc	36.41	±	1.89

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
pandafish-dt-7b	45.24	77.19	78.41	49.76	62.65

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	27.95	±	2.82
		acc_norm	26.38	±	2.77
agieval_logiqa_en	0	acc	39.32	±	1.92

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
HeatherSpellGen3	44.88	76.87	78.3	49.89	62.48

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	27.56	±	2.81
		acc_norm	25.20	±	2.73
agieval_logiqa_en	0	acc	39.02	±	1.91

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Mistral-7B-Instruct-v0.2	38.5	71.64	66.82	42.29	54.81

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	23.62	±	2.67
		acc_norm	22.05	±	2.61
agieval_logiqa_en	0	acc	36.10	±	1.88

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
dolphin-2.8-mistral-7b-v02	38.99	72.22	51.96	40.41	50.9

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	21.65	±	2.59
		acc_norm	20.47	±	2.54
agieval_logiqa_en	0	acc	35.79	±	1.88

tosh

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
pandafish-2-7b-32k	40.8	73.35	57.46	42.69	53.57

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	22.05	±	2.61
		acc_norm	19.69	±	2.50
agieval_logiqa_en	0	acc	35.94	±	1.88