README.md

metadata

datasets:
  - xzuyn/chatdoctor-200k-stripped
  - Technoculture/riddle_sense
  - axiong/pmc_llama_instructions
  - Open-Orca/SlimOrca-Dedup
language:
  - en
tags:
  - medical

Technoculture/MD7b-alpha adapter merged with its Base Model (Meditron 7B)

Evaluations

Open LLM Leaderboard

Model	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
MT7Bi	50.94	73.24	Error: File does not exist	43.04	72.06	22.52

ARC: 50.94%

Task	Version	Metric	Value		Stderr
arc_challenge	Yaml	acc,none	0.48
		acc_stderr,none	0.01
		acc_norm,none	0.51
		acc_norm_stderr,none	0.01
		alias	arc_challenge

HellaSwag: 73.24%

Task	Version	Metric	Value		Stderr
hellaswag	Yaml	acc,none	0.54
		acc_stderr,none	0
		acc_norm,none	0.73
		acc_norm_stderr,none	0
		alias	hellaswag

TruthfulQA: 43.04%

Task	Version	Metric	Value		Stderr
truthfulqa	N/A	bleu_max,none	16.17
		bleu_max_stderr,none	0.38
		bleu_acc,none	0.36
		bleu_acc_stderr,none	0
		bleu_diff,none	-2.78
		bleu_diff_stderr,none	0.26
		rouge1_max,none	39.99
		rouge1_max_stderr,none	0.64
		rouge1_acc,none	0.36
		rouge1_acc_stderr,none	0
		rouge1_diff,none	-4.19
		rouge1_diff_stderr,none	0.45
		rouge2_max,none	24.52
		rouge2_max_stderr,none	0.68
		rouge2_acc,none	0.29
		rouge2_acc_stderr,none	0
		rouge2_diff,none	-4.90
		rouge2_diff_stderr,none	0.55
		rougeL_max,none	36.52
		rougeL_max_stderr,none	0.64
		rougeL_acc,none	0.33
		rougeL_acc_stderr,none	0
		rougeL_diff,none	-4.56
		rougeL_diff_stderr,none	0.45
		acc,none	0.33
		acc_stderr,none	0.05
		alias	truthfulqa
truthfulqa_gen	Yaml	bleu_max,none	16.17
		bleu_max_stderr,none	0.61
		bleu_acc,none	0.36
		bleu_acc_stderr,none	0.02
		bleu_diff,none	-2.78
		bleu_diff_stderr,none	0.51
		rouge1_max,none	39.99
		rouge1_max_stderr,none	0.80
		rouge1_acc,none	0.36
		rouge1_acc_stderr,none	0.02
		rouge1_diff,none	-4.19
		rouge1_diff_stderr,none	0.67
		rouge2_max,none	24.52
		rouge2_max_stderr,none	0.83
		rouge2_acc,none	0.29
		rouge2_acc_stderr,none	0.02
		rouge2_diff,none	-4.90
		rouge2_diff_stderr,none	0.74
		rougeL_max,none	36.52
		rougeL_max_stderr,none	0.80
		rougeL_acc,none	0.33
		rougeL_acc_stderr,none	0.02
		rougeL_diff,none	-4.56
		rougeL_diff_stderr,none	0.67
		alias	- truthfulqa_gen
truthfulqa_mc1	Yaml	acc,none	0.28
		acc_stderr,none	0.02
		alias	- truthfulqa_mc1
truthfulqa_mc2	Yaml	acc,none	0.43
		acc_stderr,none	0.01
		alias	- truthfulqa_mc2

Winogrande: 72.06%

Task	Version	Metric	Value		Stderr
winogrande	Yaml	acc,none	0.72
		acc_stderr,none	0.01
		alias	winogrande

GSM8K: 22.52%

Task	Version	Metric	Value		Stderr
gsm8k	Yaml	exact_match,get-answer	0.23
		exact_match_stderr,get-answer	0.01
		alias	gsm8k

Elapsed time: 03:56:55