Commit graph

4630 commits

Author SHA1 Message Date
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
Jacksonxhx
961146ef3e update milvus integration 2024-08-20 17:19:35 +08:00
莘权 马
8d6e2e33a5 feat: + python <3.12 2024-08-18 11:31:26 +08:00
JGalego
61141e97b9 Added support for Command R/R+ 2024-08-17 03:57:38 +01:00
JGalego
4d59dd69cc Added Mistral Small 2024-08-17 03:20:39 +01:00
JGalego
ddb5409118 Fixed max tokens; Corrected typo 2024-08-17 03:10:06 +01:00
JGalego
58a5720f01 Added streaming support for Jamba-Instruct 2024-08-17 01:56:15 +01:00
JGalego
d65e5556dd Refactored Ai21Provider to add support for Jamba-Instruct 2024-08-17 01:38:17 +01:00
JGalego
9f9e405e86 Updated bedrock supported models 2024-08-17 00:55:20 +01:00
JGalego
adecdf1764 Refactored BedrockLLM client to accept temp creds via env vars 2024-08-17 00:53:26 +01:00
Zhaoyang Yu
c9989c069e Update llm.py 2024-08-15 20:21:07 +08:00
Jacksonxhx
986fb784aa integrate milvus 2024-08-14 18:16:18 +08:00
Jacksonxhx
490203d20f integrated milvus 2024-08-14 16:27:30 +08:00
better629
ab846f65e4
Merge pull request #1437 from iorisa/feature/qianfan
feat: upgrade qianfan package
2024-08-07 17:33:52 +08:00
better629
42907e9c1f
Merge branch 'main' into feature/qianfan 2024-08-07 17:33:25 +08:00
better629
48de3f97eb
Merge pull request #1438 from iorisa/fixbug/1429
fixbug: there's a problem about using external LLM of huoshan #1429
2024-08-07 17:31:26 +08:00
better629
d73cc94356
Merge pull request #1433 from iorisa/fixbug/1422
fixbug: #1422 Role's validate_role_extra resets watch in Environment obj deserialization
2024-08-07 17:26:32 +08:00
莘权 马
c886d018e0 feat: +ark llm 2024-08-07 15:01:38 +08:00
莘权 马
945c24ae15 fixbug: unit test 2024-08-07 14:53:37 +08:00
better629
9d38a30ca8
Merge pull request #1432 from iorisa/fixbug/1424
fixbug: #1424 Add GPT-4o/GPT-4o-mini support
2024-08-07 14:12:51 +08:00
Guess
833321c7ed
Merge pull request #1431 from iorisa/fixbug/1430
fixbug: #1430 DO NOT FORCE VALIDATE '{'Required Python packages'}' by default
2024-08-07 14:01:47 +08:00
femto
f6cbf06e7b rm sk agent 2024-08-07 13:13:57 +08:00
femto
bfc7d6b134 rm sk agent 2024-08-07 13:13:34 +08:00
莘权 马
76a0271701 feat: merge geekan:main 2024-08-06 17:07:03 +08:00
莘权 马
09d07393fb feat: merge geekan:main 2024-08-06 16:59:33 +08:00
莘权 马
f39658db2b feat: merge main 2024-08-06 16:27:01 +08:00
莘权 马
f19fcfa2df feat: merge main 2024-08-06 16:22:42 +08:00
莘权 马
534e231195 feat: merge main 2024-08-06 16:09:37 +08:00
莘权 马
8a92fa0f36 feat: merge main 2024-08-06 16:07:32 +08:00
莘权 马
9086cccc49 fixbug: Optional not working 2024-08-06 15:33:25 +08:00
莘权 马
284699224e fixbug: Optional not working 2024-08-06 15:29:10 +08:00