Commit Graph

113 Commits

Author SHA1 Message Date
Zequn Liu
ff2c15a09f
[fix] summarizer debug logger (#417) 2023-09-20 15:29:26 +08:00
Yike Yuan
bd50bad8b5
[Feat] Support mm models on public dataset and fix several issues. (#412)
* [Feat] Add public dataset support for visualglm, qwenvl, and flamingo

* [Fix] MMBench related changes.

* [Fix] Openflamingo inference.

* [Fix] Hide ckpt path.

* [Fix] Pre-commit.

---------

Co-authored-by: Haodong Duan <dhd.efz@gmail.com>
2023-09-19 19:08:44 +08:00
Yuanhan Zhang
7c2726c23b
[Model] Yhzhang/add mlugowl llamaadapter (#405)
* refine gitignore

* [Feature]: Add minigpt-4

* [Feature]: Add mm local runner

* [Feature]: Add instructblip

* add otter and llama-adapter

* add owl

* add llama2-adapter and owl

* lint

* [Feature]: Add minigpt-4

* [Feature]: Add instructblip

* add otter and llama-adapter

* add owl

* add llama2-adapter and owl

* lint

* lint

* update

* lint

* lint

* add __init__.py

* update

* update

* update

* update

* [Feature]: Add minigpt-4

* [Feature]: Add mm local runner

* [Feature]: Add instructblip

* add otter and llama-adapter

* add owl

* add llama2-adapter and owl

* lint

* [Feature]: Add minigpt-4

* [Feature]: Add instructblip

* add otter and llama-adapter

* add owl

* add llama2-adapter and owl

* lint

* lint

* update

* lint

* lint

* add __init__.py

* update

* update

* update

* update

* optimize mmbench dataset args

* update

* update

* run commit hook

---------

Co-authored-by: liuyuan <3463423099@qq.com>
Co-authored-by: kennymckormick <dhd@pku.edu.cn>
Co-authored-by: kennymckormick <dhd.efz@gmail.com>
2023-09-19 14:21:26 +08:00
so2liu
267401bded
[Feat] add custom summarizer argument in CLI run mode 在CLI启动模式中添加自定义Summarizer参数 (#411)
* feat: add custom summarizer in CLI run mode

* feat: search local config by match_cfg_file
2023-09-18 18:11:22 +08:00
Hubert
2c15a0c01d
[Feat] refine docs and codes for more user guides (#409) 2023-09-18 16:12:13 +08:00
Hubert
a11cb45c83
[Feat] implementation for support promptbench (#239)
* [Feat] support adv_glue dataset for adversarial robustness

* reorg files

* minor fix

* minor fix

* support prompt bench demo

* minor fix

* minor fix

* minor fix

* minor fix

* minor fix

* minor fix

* minor fix

* minor fix
2023-09-15 15:06:53 +08:00
Hubert
de8a154795
[Feat] support ds1000 dataset (#395)
* [Feat] support ds1000 datase
2023-09-15 12:50:27 +08:00
Xidong Wang
47a752cd56
[Dataset] Add CMB (#376)
* Add CMB

* modify CMB

---------

Co-authored-by: wangxidong <xidongw@163.com>
2023-09-12 19:16:41 +08:00
cdpath
722eb39526
fix potential oom issue (#387) 2023-09-12 10:41:03 +08:00
Tong Gao
c7a8b8fe98
Bump version to 0.1.4 (#367) 2023-09-08 20:51:38 +08:00
Yixiao Fang
fada77a31c
[Feature] Add open source dataset eval config of instruct-blip (#370)
* add configs

* refactor model

* add post processor and prompt constructor
2023-09-08 15:07:09 +08:00
Leymore
49c467458f
[Feature] Update llama2 (#372) 2023-09-08 12:47:56 +08:00
Tong Gao
b11838f80a
[Feature] Update claude2 postprocessor (#365)
* [Feature] Update claude2 config

* [Feature] Update claude2 postprocessor
2023-09-07 11:26:26 +08:00
Yike Yuan
b885ec84df
[Feat] Support Qwen-VL-Chat on MMBench. (#312)
* [Feat] Support Qwen-VL base.

* [Feat] Support Qwen-VL-Chat on MMBench.

* [Fix] Add postprocessor and fix format.

* [Fix] Add type hint and remove redundant codes.

* [Fix] fix bugs in postprocessor.

* [Fix] Use given commit id.
2023-09-06 18:42:19 +08:00
Hubert
ddb8197212
[Feat] support wizardcoder series (#344)
* [Feat] support wizardcoder series

* minor fix
2023-09-06 17:52:35 +08:00
Leymore
880b34e759
[Fix] Quick lint fix (#362)
* add default value

* lint fix

* use None
2023-09-06 14:33:13 +08:00
Tong Gao
5d75c1bbb9
[Enhancement] Increase default task size (#360) 2023-09-05 10:38:13 +08:00
Leymore
b8bf16e81c
[Fix] zero retriever add default value (#361) 2023-09-05 10:37:42 +08:00
Mashiro
ab21f3be66
[Enhance] Supress warning raised by get_logger (#353) 2023-09-04 15:27:08 +08:00
Leymore
a1782f9a08
[Fix] triviaqa & nq postprocess (#350) 2023-09-04 15:24:52 +08:00
Tong Gao
ce65d3393b
[Sync] Use finally to clean up temp files (#337) 2023-09-04 15:20:16 +08:00
Yixiao Fang
2cd994c3d1
[Fix] add import check of multimodal (#352) 2023-09-04 14:41:07 +08:00
Leymore
8774465a8f
[Enhancement] ignore ZeroRetriever error when id_list provided (#340) 2023-09-04 11:12:16 +08:00
Yuanhan Zhang
f2dd98ca7a
[Feat] Support LLaVA and mPLUG-Owl (#331)
* refine gitignore

* [Feature]: Add minigpt-4

* [Feature]: Add mm local runner

* [Feature]: Add instructblip

* add otter and llama-adapter

* add owl

* add llama2-adapter and owl

* lint

* [Feature]: Add minigpt-4

* [Feature]: Add instructblip

* add otter and llama-adapter

* add owl

* add llama2-adapter and owl

* lint

* lint

* update

* lint

* lint

* add __init__.py

* update

* update

* update

---------

Co-authored-by: liuyuan <3463423099@qq.com>
2023-09-01 23:32:05 +08:00
Leymore
e810974068
[Fix] Fix when missing both pad and eos token (#287)
* fix when missing both pad and eos token

* update pad_token_id impl
2023-08-31 16:53:39 +08:00
Li Bo
a4d6840739
[Feat] Add Otter to OpenCompass MMBench Evaluation (#232)
* add otter model for opencompass mmbench

* add docs

* add readme docs

* debug for otter opencomass eval

* delete unused folders

* change to default data path

* remove unused files

* remove unused files

* update

* update config file

* flake8 lint formated and add prompt generator

* add prompt generator to config

* add a specific postproecss

* add post processor

* add post processor

* add post processor

* update according to suggestions

* remove unused redefinition
2023-08-31 12:55:53 +08:00
Leymore
7ca6ba625e
[Feature] Add qwen & qwen-chat support (#286)
* add and apply update suffix tool

* add tool doc

* add qwen configs

* add cmmlu

* rename bbh

* update datasets

* delete

* update hf_qwen_7b.py
2023-08-31 11:29:05 +08:00
Hubert
fd389e2d78
[Feat] support codellama and preds collection tools (#335) 2023-08-31 11:14:42 +08:00
Tong Gao
9058be07b8
[Feature] Simplify entry script (#204)
* [Feature] Simply entry script

* update
2023-08-25 17:36:30 +08:00
Tong Gao
f480b72703
[Feature] Support model-bound prediction postprocessor, use it in Claude (#268)
* [Feature] Support model-bound text postprocessor, add claude as an example

* update

* update

* minor fix

---------

Co-authored-by: zhoufengzhe <zhoufengzhe@pjlab.org.cn>
2023-08-25 16:12:21 +08:00
Yike Yuan
3f601f420b
[Feat] Support public dataset of visualglm and llava. (#265)
* [Feat] Add public dataset support of VisualGLM.

* [Feat] Refactor LLaVA.

* [Feat] Add public dataset support of LlaVA.

* [Fix] Add  arg.
2023-08-25 15:44:32 +08:00
Yuan Liu
dc6e54f6f4
[Feature]: Verify the acc of these public datasets (#269)
* [Feature]: Refactor public dataset eval

* [Feature]: Verify public dataset acc
2023-08-25 15:01:58 +08:00
philipwangOvO
3f37c40aa3
[Dataset] Refactor LEval 2023-08-25 11:46:23 +08:00
Tong Gao
60c2d3d76b
[Feature] Add Claude support (#253)
* [Feature] Add Claude support

* [Feature] Add Claude support

* Update opencompass/models/claude_api.py

Co-authored-by: Hubert <42952108+yingfhu@users.noreply.github.com>

* raise import erorr

---------

Co-authored-by: Hubert <42952108+yingfhu@users.noreply.github.com>
2023-08-24 14:29:45 +08:00
Yuan Liu
343f785b07
[Feature]: Add Flamingo (#258)
* [Feature]: Add Openflamingo MMBench

* [Fix]: Fix import error

* [Fix]: Revert task config

* [Fix]: Fix path bug
2023-08-24 14:11:29 +08:00
LZHgrla
77745a84ea
[Fix] Fix bugs for PeftModel generate (#252)
* fix bugs

* fix typo
2023-08-24 14:07:33 +08:00
Tong Gao
bd47a00f27
[Fix] use sympy only when necessary (#255) 2023-08-24 10:15:20 +08:00
Tong Gao
01372a4806
update (#251) 2023-08-23 16:25:23 +08:00
Yixiao Fang
1034c487ef
[Refactor] Refactor instructblip (#227)
* refactor instructblip

* add post processor

* add forward

* fix lint

* update

* update
2023-08-23 15:33:59 +08:00
liushz
02ce139bc6
[Feature] Add Tree-of-Thought method (#173)
* Add ToT method

* Update ToT

* Update ToT

* Update ToT

* Update ToT

* Update ToT

* Update ToT

* Update ToT

* Update chain_of_thought.md

* Update icl_tot_inferencer.py

---------

Co-authored-by: liuhongwei <liuhongwei@pjlab.org.cn>
2023-08-23 12:23:05 +08:00
Leymore
ff5ab92331
[Feature] Add llama2 native implements (#235)
* add llama2 native implements

* rename configs/eval_llama_7b.py

---------

Co-authored-by: zhoufengzhe <zhoufengzhe@pjlab.org.cn>
2023-08-23 11:33:25 +08:00
Leymore
fdc69f9d58
[Fix] local runner debug (#238) 2023-08-21 16:58:36 +08:00
Yike Yuan
8d368d1cd6
[Feat] Support visualglm and llava for MMBench evaluation. (#211)
* [Feat] Support visualglm inference on MMBench.

* [Feat] Support llava inference on MMBench.

* [Fix] Fix pre-commit format.

* [Fix] Add docstring for llava

* [Fix] Fix multi-process inference error of LlaVA and add comments.
1. Set `low_cpu_mem_usage` to False to address device issue.
2. Add docstring and type hints.
3. Rename class and remove registry.

* [Fix] Pre-commit fix.

* [Fix] add forward entry, add dynamic import to seedbench

* [Fix] Fix pre-commit.

* [Fix] Fix missing context.

* [Fix] Fix docstring.
2023-08-21 15:57:30 +08:00
Yike Yuan
a6552224cb
[Feat] Support multi-modal evaluation on MME benchmark. (#197)
* [Feat] Support multi-modal evaluation on MME benchmark.

* [Fix] Remove debug code.

* [Fix] Remove redundant codes and add type hints.

* [Fix] Rename in config.

* [Fix] Rebase main.

* [Fix] Fix isort and yapf conflict.
2023-08-21 15:53:20 +08:00
philipwangOvO
3b29aaee2b
[Fix] bin_trim (#237)
Co-authored-by: wangchonghua <wangchonghua@pjlab.org.cn>
2023-08-21 15:44:49 +08:00
philipwangOvO
655a807f4b
[Dataset] LongBench (#236)
Co-authored-by: wangchonghua <wangchonghua@pjlab.org.cn>
2023-08-21 14:15:20 +08:00
Yixiao Fang
0fa2482661
[Feature] Support SEED-Bench (#203)
* support seedbench

* update docstrings

* update

* update

* update

* update according to review

* rebase

* fix lint

* update
2023-08-17 17:24:02 +08:00
Ezra-Yu
17ccaa5980
[Feat] Add codegeex2 and Humanevalx (#210)
* add codegeex2

* add humanevalx dataset

* add evaluator

* update evaluator

* update configs

* update clean code

* update configs

* fix lint

* remove sleep

* fix lint

* update docs

* fix lint
2023-08-17 11:03:16 +08:00
Hubert
0fe2366a72
[Feat] support adv_glue dataset for adversarial robustness (#205)
* [Feat] support adv_glue dataset for adversarial robustness

* reorg files

* minor fix

* minor fix
2023-08-16 18:42:06 +08:00
Yuan Liu
78df9bd0cb
[Feature]: Add other public datasets (#206)
* [Feature]: Refactor class name

* [Feature]: Add minigpt-4 coco caption

* [Feature]: Update minigpt-4 coco caption

* [Feature]: Add MiniGPT-4 ScienceQA

* [Feature]: Add minigpt-4 vqav2

* [Feature]: Add VSR

* [Feature]: Revert task to previous version
2023-08-16 11:37:26 +08:00