GitLab

* add needlebench

* simplify needlebench 32k, 128k, 200k for eval

* update act prompt

* fix bug in needlebench summarizer

* add needlebench intro, fix summarizer

* lint summarizer

* fix linting error

* move readme.md

* update readme for needlebench

* update docs of needlebench

* simplify needlebench summarizers

* Fixed the problem of never entering task.run() mode in local scheduling mode.

get_command_template方法中为命令行前缀添加了CUDA_VISIBLE_DEVICES=或set CUDA_VISIBLE_DEVICES=。导致task.run()分支失效。
---------
CUDA_VISIBLE_DEVICES= or set CUDA_VISIBLE_DEVICES= is added to the command line prefix in the get_command_template method. Causes the task.run() branch to fail.

* [Fix]Fixed the problem of never entering task.run() mode in local scheduling mode.

get_command_template方法中为命令行前缀添加了CUDA_VISIBLE_DEVICES=或set CUDA_VISIBLE_DEVICES=。导致task.run()分支失效。
---
CUDA_VISIBLE_DEVICES= or set CUDA_VISIBLE_DEVICES= is added to the command line prefix in the get_command_template method. Causes the task.run() branch to fail.

* [Fix]Fixed the problem of never entering task.run() mode in local scheduling mode.

get_command_template方法中为命令行前缀添加了CUDA_VISIBLE_DEVICES=或set CUDA_VISIBLE_DEVICES=。导致task.run()分支失效。
CUDA_VISIBLE_DEVICES= or set CUDA_VISIBLE_DEVICES= is added to the command line prefix in the get_command_template method. Causes the task.run() branch to fail.

* [Feature] Support OpenFinData

* add README for OpenFinData

* update README

* add gemini

* add gemini

* add gemini

* fix ifeval

* fix ifeval

* fix ifeval

* fix ifeval

* add lmdeploy pytorch model

* fix

* speed up encoding and decoding

* fix

* change tokenizer

* add global retriever config

* give zero shot overwrite example

* give zero shot overwrite example

---------
Co-authored-by: Lei Fei <SENSETIME\leifei1@cn3114002087l.domain.sensetime.com>
Co-authored-by: Leymore <zfz-960727@163.com>

* fix bug of gsm8k_postprocess

* update postprocess

---------
Co-authored-by: Lei Fei <SENSETIME\leifei1@cn3114002087l.domain.sensetime.com>
Co-authored-by: Leymore <zfz-960727@163.com>

* [feat] support humaneval_multipl-e

* format

---------
Co-authored-by: Leymore <zfz-960727@163.com>

* fix lawbench 2-1 f0.5 score calculation bug

* use path in overall datasets folder

---------
Co-authored-by: Leymore <zfz-960727@163.com>

* hotfix for mtbench

* hotfix

* add do sample demo for subjective dataset

* fix strings

* format

---------
Co-authored-by: Leymore <zfz-960727@163.com>

* support NPHardEval

* add .md file and fix minor bugs

* refactor and minor fix

---------
Co-authored-by: Leymore <zfz-960727@163.com>

* add daily test case

* Update pr-run-test.yml

* Update daily-run-test.yml

* Update daily-run-test.yml

* Update pr-run-test.yml

* Update daily-run-test.yml

* Update oc_score_assert.py

* Update daily-run-test.yml

* Update daily-run-test.yml

* Update daily-run-test.yml

* update testcase baseline

* fix test case name

* add more models into daily test

---------
Co-authored-by: zhulin1 <zhulin1@pjlab.org.cn>
Co-authored-by: Leymore <zfz-960727@163.com>

* update workflow

* another trial

* another trial

* another trial

Co-authored-by: jiangjin1999 <1261842974@qq.com>

* support alpacaeval_v1

* Update opencompass/summarizers/subjective/__init__.py
Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>

* Update opencompass/summarizers/subjective/alpacaeval_v1.py
Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>

* fix conflict

* support alpacaeval v2

* support alpacav2

---------
Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>

* add daily test case

* Update pr-run-test.yml

* Update daily-run-test.yml

* Update daily-run-test.yml

* Update pr-run-test.yml

---------
Co-authored-by: zhulin1 <zhulin1@pjlab.org.cn>

* fix

* update

* fix internlm1

* fix docs

* remove sys

* Update runtime.txt to fix rouge_chinese bugs.

the wheel file of rouge_chinese will overwrite the rouge package, causing bugs. Replacing it to the github code, which is the correct version.

* fix PEP format issues

* fix PEP format issues

* enable pip install

---------
Co-authored-by: 郭琦鹏 <guoqipeng@pjlab.org.cn>
Co-authored-by: Leymore <zfz-960727@163.com>

* Create link-check.yml

* Update link-check.yml

* Update zhipu api and fix min_out_len issue of API class

* Update example

* Update example

* [Feature] Add IFEval

* [Fix] Changing the Score Rule.

* [Feat] update cibench

* [Feat] Support CIBench

* [Feat] Support CIBench

* [Feat] Support CIBench

* [Feat] Support CIBench

* fix corev2

* fix corev2

Co-authored-by: liuhongwei <liuhongwei@pjlab.org.cn>