16 Commits

Author	SHA1	Message	Date
Sean	2b565da220	Update evaluate_plugin.py ... change Old Evaluation Dataset (Version 20230803) to new version	2024-02-17 17:27:49 +08:00
兼欣	7eb9016908	update agent benchmarks and add qwen-72b results	2023-12-06 12:57:11 +08:00
yangapku	e8e15962d8	add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support	2023-11-30 15:29:13 +08:00
yangapku	c00209f932	update evaluate scripts	2023-10-30 19:13:14 +08:00
yangapku	f076e2fa42	specify repetition penalty	2023-10-13 11:44:48 +08:00
yangapku	fc57dea277	release latest models	2023-09-25 10:41:59 +08:00
yangapku	b86a0f2c8a	update EVALUATION.md	2023-09-18 11:50:53 +08:00
feihu.hf	4864f7b278	fix format problems in evaluation code; update ceval extraction rules	2023-08-25 22:44:07 +08:00
Yang An	677180a653	Merge pull request #185 from Owen-Qin/fix_ceval ... fix bug for ceval	2023-08-15 17:55:23 +08:00
qinxy3	543ffaf617	fix code	2023-08-15 11:03:24 +08:00
qinxy3	bff91b3305	fix bug for ceval	2023-08-14 14:47:12 +08:00
Haonan Li	e7072a49c0	add CMMLU evaluation results	2023-08-13 20:58:52 +04:00
兼欣	9139fbdf99	release the evaluation benchmark for tool use; update tool use results to that of the hf version	2023-08-08 17:45:41 +08:00
feihu.hf	680a3e8bb8	update EVALUATION.md	2023-08-04 10:54:19 +08:00
feihu.hf	1134e08be7	add evaluation code for Qwen-7B-Chat	2023-08-03 23:27:48 +08:00
JustinLin610	ba2d85a13b	first commit	2023-08-03 12:57:53 +08:00