4552 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
better629	c023a235a4	fix dashscope high version problem	2024-10-10 22:07:34 +08:00
Ikko Eltociear Ashimine	d8a5a9c27c	chore: update st_role.py ... occuring -> occurring	2024-10-03 16:25:48 +09:00
Alexander Wu	bdba23e422	Merge pull request #1488 from better629/tokens ... update lastedt model usage	2024-09-29 15:38:02 +08:00
better629	325e45247e	support o1-series	2024-09-29 15:15:29 +08:00
better629	50cdecf627	simplify code	2024-09-29 14:47:25 +08:00
better629	f7dd8c965e	update close-source latest model usage	2024-09-29 14:38:11 +08:00
better629	91c2729112	Merge pull request #1486 from IcarusAegis/add_token ... Added token cost and MAX token for Qwen 2.5 series	2024-09-29 11:31:20 +08:00
IcarusAegis	65f2cae6c0	Add Qwen2.5 tokens_counter	2024-09-27 14:38:09 +08:00
didi	040a7324eb	Update test_curve.py	2024-09-26 21:56:54 +08:00
didi	e8f6186a56	update	2024-09-26 20:06:57 +08:00
didi	f14830b16a	Update optimizer.py	2024-09-25 16:47:12 +08:00
didi	8dfe2de34c	Update	2024-09-25 16:46:20 +08:00
ChengZi	4d92fdcec9	lazy dependency for milvus ... Signed-off-by: ChengZi <chen.zhang@zilliz.com>	2024-09-25 14:11:21 +08:00
ChengZi	e5f037f86d	update dependency ... Signed-off-by: ChengZi <chen.zhang@zilliz.com>	2024-09-25 11:09:08 +08:00
didi	6a84a9d49b	Update HumanEval Eval	2024-09-24 19:28:03 +08:00
didi	c7f44e956d	Update	2024-09-22 21:45:53 +08:00
didi	99a9f7b6e9	update humaneval data path and add baseline data	2024-09-22 19:35:06 +08:00
didi	e3bcedc298	Update Benchmark's data	2024-09-22 15:54:32 +08:00
didi	22e8f9d7fc	Update baseline and benchmark; update evaluator	2024-09-22 15:46:50 +08:00
didi	63f3f884c9	Update for fengwei	2024-09-16 18:13:30 +08:00
didi	53890a5f86	更新了HotpotQA BenchMark 代码与对应的Self Consistency 实现	2024-09-13 12:56:18 +08:00
didi	0704f341de	更新了eval索引的入口	2024-09-11 17:53:52 +08:00
didi	b805da0bbe	更新了eval BUG，同时更新了新的baseline	2024-09-11 17:00:14 +08:00
didi	b9a2d94da2	更新了xml-compile方法，更新了剩余Baseline	2024-09-11 15:21:33 +08:00
Zhaoyang Yu	f691c5f439	Update QA	2024-09-10 21:51:38 +08:00
didi	1de0653d70	Update token_counter.py	2024-09-10 19:07:50 +08:00
didi	bdf865eb0d	Merge branch 'main' of https://github.com/didiforgithub/MetaGPT-MathAI	2024-09-10 19:06:17 +08:00
didi	7f45ef6231	Merge branch 'main' of https://github.com/didiforgithub/MetaGPT-MathAI	2024-09-10 19:04:05 +08:00
Zhaoyang Yu	445a2e6048	Update QA	2024-09-10 18:59:13 +08:00
didi	ab112462a5	添加了cost计算	2024-09-10 18:51:18 +08:00
Zhaoyang Yu	257b994409	Update drop.py	2024-09-10 18:45:54 +08:00
Zhaoyang Yu	68e87da378	Update Hotpotqa	2024-09-10 18:27:20 +08:00
Zhaoyang Yu	4ce18d7f48	Update baselines	2024-09-10 16:51:26 +08:00
didi	0b0a49d772	更新 hotpotqa Baseline	2024-09-10 12:48:28 +08:00
didi	c7c34cda7d	Update human Eval	2024-09-10 10:58:39 +08:00
didi	62ffa730e0	update humaneval baseline & hotpotqa baseline	2024-09-10 10:57:21 +08:00
didi	7ffe68b499	重构了Evaluator	2024-09-09 18:19:22 +08:00
didi	4e0a896bdc	提交baseline例子；修改context-fill 格式识别方式	2024-09-09 17:17:15 +08:00
didi	ca560a844f	合入Eval与Optimize ... 当前问题 1. eval 存在部分参数差异（path，csv测试） 2. optimize 尝试新流程（优化后的optimize曲线）；optimize 模版书写 3. optimize 在各个数据集上跑通 4. 创建baseline folder 5. 创建experiment data收集方法 6. 从ags中移出	2024-09-08 23:04:01 +08:00
didi	c3903412b4	Update Operator Optimize Method.	2024-09-02 16:47:03 +08:00
Maximilian Knoll	fa7e3ae24e	add authorization header to support open webui	2024-08-27 13:27:47 +02:00
didi	d97f90f9c7	Update	2024-08-26 08:40:10 +08:00
didi	7c2501e08b	Update	2024-08-26 08:30:24 +08:00
didi	6a01a679ce	test for multi llm	2024-08-25 22:17:27 +08:00
didi	1593e98c45	Update Multi LLM Config & Basic Evaluator	2024-08-25 22:16:39 +08:00
didi	a3ff25430e	Update ConText Fill	2024-08-23 20:43:29 +08:00
didi	02c7c4ea47	Update 混乱版本	2024-08-23 14:21:04 +08:00
didi	2937d9a13a	Update 粗糙版本 优化	2024-08-23 13:57:35 +08:00
莘权 马	5bec4bbaa0	fixbug: qianfan timeout	2024-08-21 14:07:10 +08:00
莘权 马	8a9cd6a2e7	fixbug: recovered role can't observe new message	2024-08-21 13:26:50 +08:00