Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * Update README.md with new features and installation instructions * Update supported models and datasets * Delete otter.py file * Fix capitalization in README.md * Update image sizes and add new features * Refactor README.md to improve readability and add new features * Add description for lmms-eval in README.md * Update accelerator support in README.md * Update lmms-eval README with improved description and additional features * Update README.md with improved task grouping description * change `Otter-AI/MME` to `lmms-lab/MME` * Update README.md * Update README.md * Remove unused code in mme.yaml * Squashed commit of the following: commit 2a45079 Author: Zhang Peiyuan <[email protected]> Date: Thu Feb 29 13:40:02 2024 +0800 Dev/py add models (#57) * add instructblip * minicpm_v * remove <image> from qwen-vl * speed up postprocessing * Optimize build context speed --------- Co-authored-by: Pu Fanyi <[email protected]> Co-authored-by: kcz358 <[email protected]> commit 7bdab7a Author: Pu Fanyi <[email protected]> Date: Wed Feb 28 14:49:07 2024 +0800 Pufanyi/flickr30k refractor (#56) * refactor vizwizvqa task * Delete vqav2_test and vqav2_val YAML files * Refactor vqav2_process_results functions * Add a pack for vqav2 * refactor okvqa * roll back vizwiz_vqa * Fix exact_match calculation in ok_vqa_process_results * Update OKVQA dataset name in readme * add model_specific_prompt_kwargs * add model_specific_prompt_kwargs to vizwiz_vqa * add model_specific_prompt_kwargs for vqav2 * lint * fix a small bug for eval_logger * Refactor make_table function to display points as " - " if value is None * Merge commit '90f42f0876a4914c5ac0d213b9dffbfb4797ff62' * Refactor ok_vqa_aggreate_submissions function * Merge commit '4afec3303a0a7ed27a8265565343bf2851b9e4c7' * Refactor VQA submission file saving * Update file utils * Merge commit 'c144b75f0c9145a625b2bbdef5123ed81e343a11' * Refactor file path handling and submission generation * OKVQA path * vizwizvqa file * pack cmmmu * fix a small metric bug for cmmmu * Add higher_is_better flag to submission metric * Add CMMMU dataset to README.md * Add logging and refactor submission file generation in docvqa utils.py * pack docvqa * add traceback to print detailed error * Refactor docvqa_test_aggregate_results to accept additional arguments * Add metric check in evaluator.py and update test.yaml and val.yaml * add common `EvalAIAnswerProcessor` for okvqa, textvqa, vizwizvqa and vqav2 * merge textvqa * textvqa * Modify submission file generation for COCO test results * Update test result storage path * update coco cap file name * Update COCO 2017 Caption dataset name * ferret * Add Ferret dataset * Refactor hb_doc_to_text function to include model-specific prompts * Add IconQA and its subtasks * Refactor image list creation in doc_to_visual function * Add process_results function to default template * Update process_results function in iconqa utils.py * refactor flickr30k * change aggregation function * Fix formatting issues and update logging message * Fix llava can not handle only text question (no visuals) * Fix qwen can not handle no image question (no visuals) * Add fuyu prepare accelerator scripts * refactor mme * naming consistency * aggregation_submissions consistency * flickr30k naming consistency * remove submissions for mme * remove unused submission function * Refactor infovqa_test.yaml and infovqa_val.yaml * Refactor code for improved readability and maintainability * stvqa * remane sqa * Update lmms_eval textcaps files and utils.py * Update default prompt for text captions * Refactor textcaps_aggregation_result function * Add generate_submission_file function and update mathvista_aggregate_results signature * Update nocaps_test.yaml and nocaps_val.yaml * refractor internal_eval * Add internal evaluation datasets * pack multidocvqa * mmvet * Fix gpt eval timeout issue for hallubench, restore load from gpt to avoid re evaluating * Refractor llava wild * Refractor llava-bench-coco * Add JSON file generation for gpt evaluation details * mmmu * Remove MMBench English and Chinese tasks * Remove unnecessary return statement in mmbench_aggregate_test_results function * Fix distributed process group initialization * Update dataset paths and group names in mmbench test configs * Update import statements in cc_utils.py, cn_utils.py, and en_utils.py * Add torch module import * lint * Remove IconQA dataset from README.md * Add Multi-DocVQA and its submodules * Add new datasets and update task names * Refactor flickr_aggregation_result function to accept additional arguments * Add timeout kwargs in Accelerator constructor * Add encoding to be utf-8 for cmmmu * Fix llava try and catch, remove torch.distributed.init in main * Ds prepare script for llava --------- Co-authored-by: JvThunder <[email protected]> Co-authored-by: kcz358 <[email protected]> commit d3dfd94 Author: Li Bo <[email protected]> Date: Tue Feb 27 22:52:07 2024 +0800 [Wandb Logger] add models, and args to wandb tables. (#55) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * add llava main in pyproject * Update README.md * Remove unnecessary dependencies and add specific version for llava_repr * Add dependencies for llava_repr*** * Update README.md * add some docs on models and command line commands * remove some lines * typo * Update model_guide.md * Update model_guide.md * Update README.md * Update README.md * Update README.md * Fix refcocog dataset path * Record gpt response in eval info * Resolve conflict * Fix hallusionbench gpt json saving path * Rename hallubench gpt output path * Change remove image to check by type instead of check by names * More robust check by type * Add timeout to API requests * Remove unnecessary img in data * Forcing an empty commit. * Testing * Delete unnecessary things * Fix error logging in get_chat_response function * Fix seedbench2 image issue in doc_to_text * Add conditional exclude for internal eval * Squashed commit of the following: commit 2fbeafc882c80242a10381abc67629d5d8b7071a Author: kcz358 <[email protected]> Date: Sat Mar 2 03:49:36 2024 +0000 Add conditional exclude for internal eval commit f188052450bed2f3a30ab6f9a6f7eb844a64cb33 Merge: a3cae8e ffb9eb2 Author: kcz358 <[email protected]> Date: Sat Mar 2 03:24:29 2024 +0000 Merge branch 'dev/readme' into kc/final_fix commit baef5905505892593fe783beb18a2de20991d6af Author: kcz358 <[email protected]> Date: Sat Mar 2 02:47:31 2024 +0000 Fix seedbench2 image issue in doc_to_text commit 11b46f3b701b79b361dd5175a263e4d89bd07fb5 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:32:49 2024 +0000 Delete unnecessary things commit 0982de2e7a2310429e51ec7828886fd49953f716 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:31:42 2024 +0000 Testing commit f840ed80f4ae467fff62b61844854a3a9e8ec8a5 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:29:30 2024 +0000 Forcing an empty commit. commit 80db78f600d07011188983637c94da84b9475fbf Merge: 786f2b5 1700786 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:24:56 2024 +0000 Merge branch 'kc/final_fix' into dev/readme commit 676229de870b8d465cef08867cd272a4b696e630 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:24:20 2024 +0000 Remove unnecessary img in data commit d293b96fb3537fea85f10f216d762abf35e05e8d Merge: 4240785 888c1c1 Author: kcz358 <[email protected]> Date: Fri Mar 1 13:41:24 2024 +0000 Merge branch 'kc/final_fix' into dev/readme commit 01bbd010590d6b7f105525580209191a1d6d5232 Author: kcz358 <[email protected]> Date: Fri Mar 1 13:40:51 2024 +0000 More robust check by type commit 66595ebc073ff9431f2400006196c0645be58ea4 Author: kcz358 <[email protected]> Date: Fri Mar 1 13:00:57 2024 +0000 Change remove image to check by type instead of check by names commit 08c2ebad1532fd6c34ac04efb94a268db9862d4f Author: kcz358 <[email protected]> Date: Fri Mar 1 12:33:02 2024 +0000 Rename hallubench gpt output path commit aefbd3c6856584135e2dcbe13381db0e0780f063 Author: kcz358 <[email protected]> Date: Fri Mar 1 09:32:52 2024 +0000 Fix hallusionbench gpt json saving path commit b9aebc3ff3b122d6d4a81bd2f28e86b2c390c505 Author: kcz358 <[email protected]> Date: Fri Mar 1 08:51:13 2024 +0000 Resolve conflict commit c9daa91f2576de69af73c80e263afb085ecd8288 Merge: 9cf86fa 93534dc Author: kcz358 <[email protected]> Date: Fri Mar 1 08:37:21 2024 +0000 Merge branch 'kc/final_fix' into dev/readme commit b1c4c88b9b36e02e9ed738ff9217d98a5ef2117b Author: kcz358 <[email protected]> Date: Fri Mar 1 07:55:03 2024 +0000 Record gpt response in eval info commit b35bc4a6c8fd6b4b2a68bb3054878807b8b92281 Author: kcz358 <[email protected]> Date: Fri Mar 1 07:49:01 2024 +0000 Fix refcocog dataset path commit 2a45079 Author: Zhang Peiyuan <[email protected]> Date: Thu Feb 29 13:40:02 2024 +0800 Dev/py add models (#57) * add instructblip * minicpm_v * remove <image> from qwen-vl * speed up postprocessing * Optimize build context speed --------- Co-authored-by: Pu Fanyi <[email protected]> Co-authored-by: kcz358 <[email protected]> commit 7bdab7a Author: Pu Fanyi <[email protected]> Date: Wed Feb 28 14:49:07 2024 +0800 Pufanyi/flickr30k refractor (#56) * refactor vizwizvqa task * Delete vqav2_test and vqav2_val YAML files * Refactor vqav2_process_results functions * Add a pack for vqav2 * refactor okvqa * roll back vizwiz_vqa * Fix exact_match calculation in ok_vqa_process_results * Update OKVQA dataset name in readme * add model_specific_prompt_kwargs * add model_specific_prompt_kwargs to vizwiz_vqa * add model_specific_prompt_kwargs for vqav2 * lint * fix a small bug for eval_logger * Refactor make_table function to display points as " - " if value is None * Merge commit '90f42f0876a4914c5ac0d213b9dffbfb4797ff62' * Refactor ok_vqa_aggreate_submissions function * Merge commit '4afec3303a0a7ed27a8265565343bf2851b9e4c7' * Refactor VQA submission file saving * Update file utils * Merge commit 'c144b75f0c9145a625b2bbdef5123ed81e343a11' * Refactor file path handling and submission generation * OKVQA path * vizwizvqa file * pack cmmmu * fix a small metric bug for cmmmu * Add higher_is_better flag to submission metric * Add CMMMU dataset to README.md * Add logging and refactor submission file generation in docvqa utils.py * pack docvqa * add traceback to print detailed error * Refactor docvqa_test_aggregate_results to accept additional arguments * Add metric check in evaluator.py and update test.yaml and val.yaml * add common `EvalAIAnswerProcessor` for okvqa, textvqa, vizwizvqa and vqav2 * merge textvqa * textvqa * Modify submission file generation for COCO test results * Update test result storage path * update coco cap file name * Update COCO 2017 Caption dataset name * ferret * Add Ferret dataset * Refactor hb_doc_to_text function to include model-specific prompts * Add IconQA and its subtasks * Refactor image list creation in doc_to_visual function * Add process_results function to default template * Update process_results function in iconqa utils.py * refactor flickr30k * change aggregation function * Fix formatting issues and update logging message * Fix llava can not handle only text question (no visuals) * Fix qwen can not handle no image question (no visuals) * Add fuyu prepare accelerator scripts * refactor mme * naming consistency * aggregation_submissions consistency * flickr30k naming consistency * remove submissions for mme * remove unused submission function * Refactor infovqa_test.yaml and infovqa_val.yaml * Refactor code for improved readability and maintainability * stvqa * remane sqa * Update lmms_eval textcaps files and utils.py * Update default prompt for text captions * Refactor textcaps_aggregation_result function * Add generate_submission_file function and update mathvista_aggregate_results signature * Update nocaps_test.yaml and nocaps_val.yaml * refractor internal_eval * Add internal evaluation datasets * pack multidocvqa * mmvet * Fix gpt eval timeout issue for hallubench, restore load from gpt to avoid re evaluating * Refractor llava wild * Refractor llava-bench-coco * Add JSON file generation for gpt evaluation details * mmmu * Remove MMBench English and Chinese tasks * Remove unnecessary return statement in mmbench_aggregate_test_results function * Fix distributed process group initialization * Update dataset paths and group names in mmbench test configs * Update import statements in cc_utils.py, cn_utils.py, and en_utils.py * Add torch module import * lint * Remove IconQA dataset from README.md * Add Multi-DocVQA and its submodules * Add new datasets and update task names * Refactor flickr_aggregation_result function to accept additional arguments * Add timeout kwargs in Accelerator constructor * Add encoding to be utf-8 for cmmmu * Fix llava try and catch, remove torch.distributed.init in main * Ds prepare script for llava --------- Co-authored-by: JvThunder <[email protected]> Co-authored-by: kcz358 <[email protected]> commit d3dfd94 Author: Li Bo <[email protected]> Date: Tue Feb 27 22:52:07 2024 +0800 [Wandb Logger] add models, and args to wandb tables. (#55) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * Fix small bugs in list_with_num * Revise list_with_num model args * Dev/readme rm rolling (#60) * remove log_likelyhood_rolling * Update time efficiency benchmark in README.md * add task guide --------- Co-authored-by: jzhang38 <[email protected]> Co-authored-by: kcz358 <[email protected]> * Remove unnecessary code and update dependencies * Fix logging utils bug on wandb grouping * Add reproduce envs * Squashed commit of the following: commit 556b12620379d79c9ed5ddba0856063b498f917c Merge: 2475639 f89a736 Author: kcz358 <[email protected]> Date: Sun Mar 3 22:12:12 2024 +0800 Merge branch 'main' into kc/final_fix commit 9509a782c9e9824273cefb1dc9671c92b887697d Author: kcz358 <[email protected]> Date: Sun Mar 3 22:11:04 2024 +0800 Add reproduce envs commit 0bff98b Author: kcz358 <[email protected]> Date: Sun Mar 3 21:19:15 2024 +0800 [Fix] wandb group logging missing columns (#61) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * Update README.md with new features and installation instructions * Update supported models and datasets * Delete otter.py file * Fix capitalization in README.md * Update image sizes and add new features * Refactor README.md to improve readability and add new features * Add description for lmms-eval in README.md * Update accelerator support in README.md * Update lmms-eval README with improved description and additional features * Update README.md with improved task grouping description * change `Otter-AI/MME` to `lmms-lab/MME` * Update README.md * Update README.md * Remove unused code in mme.yaml * Squashed commit of the following: commit 2a45079 Author: Zhang Peiyuan <[email protected]> Date: Thu Feb 29 13:40:02 2024 +0800 Dev/py add models (#57) * add instructblip * minicpm_v * remove <image> from qwen-vl * speed up postprocessing * Optimize build context speed --------- Co-authored-by: Pu Fanyi <[email protected]> Co-authored-by: kcz358 <[email protected]> commit 7bdab7a Author: Pu Fanyi <[email protected]> Date: Wed Feb 28 14:49:07 2024 +0800 Pufanyi/flickr30k refractor (#56) * refactor vizwizvqa task * Delete vqav2_test and vqav2_val YAML files * Refactor vqav2_process_results functions * Add a pack for vqav2 * refactor okvqa * roll back vizwiz_vqa * Fix exact_match calculation in ok_vqa_process_results * Update OKVQA dataset name in readme * add model_specific_prompt_kwargs * add model_specific_prompt_kwargs to vizwiz_vqa * add model_specific_prompt_kwargs for vqav2 * lint * fix a small bug for eval_logger * Refactor make_table function to display points as " - " if value is None * Merge commit '90f42f0876a4914c5ac0d213b9dffbfb4797ff62' * Refactor ok_vqa_aggreate_submissions function * Merge commit '4afec3303a0a7ed27a8265565343bf2851b9e4c7' * Refactor VQA submission file saving * Update file utils * Merge commit 'c144b75f0c9145a625b2bbdef5123ed81e343a11' * Refactor file path handling and submission generation * OKVQA path * vizwizvqa file * pack cmmmu * fix a small metric bug for cmmmu * Add higher_is_better flag to submission metric * Add CMMMU dataset to README.md * Add logging and refactor submission file generation in docvqa utils.py * pack docvqa * add traceback to print detailed error * Refactor docvqa_test_aggregate_results to accept additional arguments * Add metric check in evaluator.py and update test.yaml and val.yaml * add common `EvalAIAnswerProcessor` for okvqa, textvqa, vizwizvqa and vqav2 * merge textvqa * textvqa * Modify submission file generation for COCO test results * Update test result storage path * update coco cap file name * Update COCO 2017 Caption dataset name * ferret * Add Ferret dataset * Refactor hb_doc_to_text function to include model-specific prompts * Add IconQA and its subtasks * Refactor image list creation in doc_to_visual function * Add process_results function to default template * Update process_results function in iconqa utils.py * refactor flickr30k * change aggregation function * Fix formatting issues and update logging message * Fix llava can not handle only text question (no visuals) * Fix qwen can not handle no image question (no visuals) * Add fuyu prepare accelerator scripts * refactor mme * naming consistency * aggregation_submissions consistency * flickr30k naming consistency * remove submissions for mme * remove unused submission function * Refactor infovqa_test.yaml and infovqa_val.yaml * Refactor code for improved readability and maintainability * stvqa * remane sqa * Update lmms_eval textcaps files and utils.py * Update default prompt for text captions * Refactor textcaps_aggregation_result function * Add generate_submission_file function and update mathvista_aggregate_results signature * Update nocaps_test.yaml and nocaps_val.yaml * refractor internal_eval * Add internal evaluation datasets * pack multidocvqa * mmvet * Fix gpt eval timeout issue for hallubench, restore load from gpt to avoid re evaluating * Refractor llava wild * Refractor llava-bench-coco * Add JSON file generation for gpt evaluation details * mmmu * Remove MMBench English and Chinese tasks * Remove unnecessary return statement in mmbench_aggregate_test_results function * Fix distributed process group initialization * Update dataset paths and group names in mmbench test configs * Update import statements in cc_utils.py, cn_utils.py, and en_utils.py * Add torch module import * lint * Remove IconQA dataset from README.md * Add Multi-DocVQA and its submodules * Add new datasets and update task names * Refactor flickr_aggregation_result function to accept additional arguments * Add timeout kwargs in Accelerator constructor * Add encoding to be utf-8 for cmmmu * Fix llava try and catch, remove torch.distributed.init in main * Ds prepare script for llava --------- Co-authored-by: JvThunder <[email protected]> Co-authored-by: kcz358 <[email protected]> commit d3dfd94 Author: Li Bo <[email protected]> Date: Tue Feb 27 22:52:07 2024 +0800 [Wandb Logger] add models, and args to wandb tables. (#55) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * add llava main in pyproject * Update README.md * Remove unnecessary dependencies and add specific version for llava_repr * Add dependencies for llava_repr*** * Update README.md * add some docs on models and command line commands * remove some lines * typo * Update model_guide.md * Update model_guide.md * Update README.md * Update README.md * Update README.md * Fix refcocog dataset path * Record gpt response in eval info * Resolve conflict * Fix hallusionbench gpt json saving path * Rename hallubench gpt output path * Change remove image to check by type instead of check by names * More robust check by type * Remove unnecessary img in data * Forcing an empty commit. * Testing * Delete unnecessary things * Fix seedbench2 image issue in doc_to_text * Add conditional exclude for internal eval * Fix small bugs in list_with_num * Revise list_with_num model args * Fix logging utils bug on wandb grouping --------- Co-authored-by: Bo Li <[email protected]> Co-authored-by: Fanyi Pu <[email protected]> Co-authored-by: jzhang38 <[email protected]> commit 7c4501a32bbb415ba7e62e93194b37ba9a435cf5 Merge: 83358a4 5e1c9c7 Author: kcz358 <[email protected]> Date: Sun Mar 3 07:25:48 2024 +0000 Merge branch 'main' into kc/final_fix commit 5c419f9fa23616a63a0bd584f18e509bb7704b50 Author: kcz358 <[email protected]> Date: Sun Mar 3 07:23:19 2024 +0000 Fix logging utils bug on wandb grouping commit 0010d0a Author: kcz358 <[email protected]> Date: Sun Mar 3 13:01:11 2024 +0800 [Fix] refcocog dataset path, record gpt prompt in internal eval, build context issue (#59) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * Update README.md with new features and installation instructions * Update supported models and datasets * Delete otter.py file * Fix capitalization in README.md * Update image sizes and add new features * Refactor README.md to improve readability and add new features * Add description for lmms-eval in README.md * Update accelerator support in README.md * Update lmms-eval README with improved description and additional features * Update README.md with improved task grouping description * change `Otter-AI/MME` to `lmms-lab/MME` * Update README.md * Update README.md * Remove unused code in mme.yaml * Squashed commit of the following: commit 2a45079 Author: Zhang Peiyuan <[email protected]> Date: Thu Feb 29 13:40:02 2024 +0800 Dev/py add models (#57) * add instructblip * minicpm_v * remove <image> from qwen-vl * speed up postprocessing * Optimize build context speed --------- Co-authored-by: Pu Fanyi <[email protected]> Co-authored-by: kcz358 <[email protected]> commit 7bdab7a Author: Pu Fanyi <[email protected]> Date: Wed Feb 28 14:49:07 2024 +0800 Pufanyi/flickr30k refractor (#56) * refactor vizwizvqa task * Delete vqav2_test and vqav2_val YAML files * Refactor vqav2_process_results functions * Add a pack for vqav2 * refactor okvqa * roll back vizwiz_vqa * Fix exact_match calculation in ok_vqa_process_results * Update OKVQA dataset name in readme * add model_specific_prompt_kwargs * add model_specific_prompt_kwargs to vizwiz_vqa * add model_specific_prompt_kwargs for vqav2 * lint * fix a small bug for eval_logger * Refactor make_table function to display points as " - " if value is None * Merge commit '90f42f0876a4914c5ac0d213b9dffbfb4797ff62' * Refactor ok_vqa_aggreate_submissions function * Merge commit '4afec3303a0a7ed27a8265565343bf2851b9e4c7' * Refactor VQA submission file saving * Update file utils * Merge commit 'c144b75f0c9145a625b2bbdef5123ed81e343a11' * Refactor file path handling and submission generation * OKVQA path * vizwizvqa file * pack cmmmu * fix a small metric bug for cmmmu * Add higher_is_better flag to submission metric * Add CMMMU dataset to README.md * Add logging and refactor submission file generation in docvqa utils.py * pack docvqa * add traceback to print detailed error * Refactor docvqa_test_aggregate_results to accept additional arguments * Add metric check in evaluator.py and update test.yaml and val.yaml * add common `EvalAIAnswerProcessor` for okvqa, textvqa, vizwizvqa and vqav2 * merge textvqa * textvqa * Modify submission file generation for COCO test results * Update test result storage path * update coco cap file name * Update COCO 2017 Caption dataset name * ferret * Add Ferret dataset * Refactor hb_doc_to_text function to include model-specific prompts * Add IconQA and its subtasks * Refactor image list creation in doc_to_visual function * Add process_results function to default template * Update process_results function in iconqa utils.py * refactor flickr30k * change aggregation function * Fix formatting issues and update logging message * Fix llava can not handle only text question (no visuals) * Fix qwen can not handle no image question (no visuals) * Add fuyu prepare accelerator scripts * refactor mme * naming consistency * aggregation_submissions consistency * flickr30k naming consistency * remove submissions for mme * remove unused submission function * Refactor infovqa_test.yaml and infovqa_val.yaml * Refactor code for improved readability and maintainability * stvqa * remane sqa * Update lmms_eval textcaps files and utils.py * Update default prompt for text captions * Refactor textcaps_aggregation_result function * Add generate_submission_file function and update mathvista_aggregate_results signature * Update nocaps_test.yaml and nocaps_val.yaml * refractor internal_eval * Add internal evaluation datasets * pack multidocvqa * mmvet * Fix gpt eval timeout issue for hallubench, restore load from gpt to avoid re evaluating * Refractor llava wild * Refractor llava-bench-coco * Add JSON file generation for gpt evaluation details * mmmu * Remove MMBench English and Chinese tasks * Remove unnecessary return statement in mmbench_aggregate_test_results function * Fix distributed process group initialization * Update dataset paths and group names in mmbench test configs * Update import statements in cc_utils.py, cn_utils.py, and en_utils.py * Add torch module import * lint * Remove IconQA dataset from README.md * Add Multi-DocVQA and its submodules * Add new datasets and update task names * Refactor flickr_aggregation_result function to accept additional arguments * Add timeout kwargs in Accelerator constructor * Add encoding to be utf-8 for cmmmu * Fix llava try and catch, remove torch.distributed.init in main * Ds prepare script for llava --------- Co-authored-by: JvThunder <[email protected]> Co-authored-by: kcz358 <[email protected]> commit d3dfd94 Author: Li Bo <[email protected]> Date: Tue Feb 27 22:52:07 2024 +0800 [Wandb Logger] add models, and args to wandb tables. (#55) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * add llava main in pyproject * Update README.md * Remove unnecessary dependencies and add specific version for llava_repr * Add dependencies for llava_repr*** * Update README.md * add some docs on models and command line commands * remove some lines * typo * Update model_guide.md * Update model_guide.md * Update README.md * Update README.md * Update README.md * Fix refcocog dataset path * Record gpt response in eval info * Resolve conflict * Fix hallusionbench gpt json saving path * Rename hallubench gpt output path * Change remove image to check by type instead of check by names * More robust check by type * Remove unnecessary img in data * Forcing an empty commit. * Testing * Delete unnecessary things * Fix seedbench2 image issue in doc_to_text * Add conditional exclude for internal eval * Fix small bugs in list_with_num * Revise list_with_num model args --------- Co-authored-by: Bo Li <[email protected]> Co-authored-by: Fanyi Pu <[email protected]> Co-authored-by: jzhang38 <[email protected]> commit b2ca65d1f12d84ae7a37ecc81f760901389a1af0 Author: kcz358 <[email protected]> Date: Sat Mar 2 05:58:08 2024 +0000 Revise list_with_num model args commit a262ea1720b2c02839d21dad2a7618bc80725f18 Author: kcz358 <[email protected]> Date: Sat Mar 2 05:09:15 2024 +0000 Fix small bugs in list_with_num commit 2fbeafc882c80242a10381abc67629d5d8b7071a Author: kcz358 <[email protected]> Date: Sat Mar 2 03:49:36 2024 +0000 Add conditional exclude for internal eval commit f188052450bed2f3a30ab6f9a6f7eb844a64cb33 Merge: a3cae8e ffb9eb2 Author: kcz358 <[email protected]> Date: Sat Mar 2 03:24:29 2024 +0000 Merge branch 'dev/readme' into kc/final_fix commit baef5905505892593fe783beb18a2de20991d6af Author: kcz358 <[email protected]> Date: Sat Mar 2 02:47:31 2024 +0000 Fix seedbench2 image issue in doc_to_text commit 11b46f3b701b79b361dd5175a263e4d89bd07fb5 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:32:49 2024 +0000 Delete unnecessary things commit 0982de2e7a2310429e51ec7828886fd49953f716 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:31:42 2024 +0000 Testing commit f840ed80f4ae467fff62b61844854a3a9e8ec8a5 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:29:30 2024 +0000 Forcing an empty commit. commit 80db78f600d07011188983637c94da84b9475fbf Merge: 786f2b5 1700786 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:24:56 2024 +0000 Merge branch 'kc/final_fix' into dev/readme commit 676229de870b8d465cef08867cd272a4b696e630 Author: kcz358 <[email protected]> Date: Fri Mar 1 15:24:20 2024 +0000 Remove unnecessary img in data commit d293b96fb3537fea85f10f216d762abf35e05e8d Merge: 4240785 888c1c1 Author: kcz358 <[email protected]> Date: Fri Mar 1 13:41:24 2024 +0000 Merge branch 'kc/final_fix' into dev/readme commit 01bbd010590d6b7f105525580209191a1d6d5232 Author: kcz358 <[email protected]> Date: Fri Mar 1 13:40:51 2024 +0000 More robust check by type commit 66595ebc073ff9431f2400006196c0645be58ea4 Author: kcz358 <[email protected]> Date: Fri Mar 1 13:00:57 2024 +0000 Change remove image to check by type instead of check by names commit 08c2ebad1532fd6c34ac04efb94a268db9862d4f Author: kcz358 <[email protected]> Date: Fri Mar 1 12:33:02 2024 +0000 Rename hallubench gpt output path commit aefbd3c6856584135e2dcbe13381db0e0780f063 Author: kcz358 <[email protected]> Date: Fri Mar 1 09:32:52 2024 +0000 Fix hallusionbench gpt json saving path commit b9aebc3ff3b122d6d4a81bd2f28e86b2c390c505 Author: kcz358 <[email protected]> Date: Fri Mar 1 08:51:13 2024 +0000 Resolve conflict commit c9daa91f2576de69af73c80e263afb085ecd8288 Merge: 9cf86fa 93534dc Author: kcz358 <[email protected]> Date: Fri Mar 1 08:37:21 2024 +0000 Merge branch 'kc/final_fix' into dev/readme commit b1c4c88b9b36e02e9ed738ff9217d98a5ef2117b Author: kcz358 <[email protected]> Date: Fri Mar 1 07:55:03 2024 +0000 Record gpt response in eval info commit b35bc4a6c8fd6b4b2a68bb3054878807b8b92281 Author: kcz358 <[email protected]> Date: Fri Mar 1 07:49:01 2024 +0000 Fix refcocog dataset path commit 2a45079 Author: Zhang Peiyuan <[email protected]> Date: Thu Feb 29 13:40:02 2024 +0800 Dev/py add models (#57) * add instructblip * minicpm_v * remove <image> from qwen-vl * speed up postprocessing * Optimize build context speed --------- Co-authored-by: Pu Fanyi <[email protected]> Co-authored-by: kcz358 <[email protected]> commit 7bdab7a Author: Pu Fanyi <[email protected]> Date: Wed Feb 28 14:49:07 2024 +0800 Pufanyi/flickr30k refractor (#56) * refactor vizwizvqa task * Delete vqav2_test and vqav2_val YAML files * Refactor vqav2_process_results functions * Add a pack for vqav2 * refactor okvqa * roll back vizwiz_vqa * Fix exact_match calculation in ok_vqa_process_results * Update OKVQA dataset name in readme * add model_specific_prompt_kwargs * add model_specific_prompt_kwargs to vizwiz_vqa * add model_specific_prompt_kwargs for vqav2 * lint * fix a small bug for eval_logger * Refactor make_table function to display points as " - " if value is None * Merge commit '90f42f0876a4914c5ac0d213b9dffbfb4797ff62' * Refactor ok_vqa_aggreate_submissions function * Merge commit '4afec3303a0a7ed27a8265565343bf2851b9e4c7' * Refactor VQA submission file saving * Update file utils * Merge commit 'c144b75f0c9145a625b2bbdef5123ed81e343a11' * Refactor file path handling and submission generation * OKVQA path * vizwizvqa file * pack cmmmu * fix a small metric bug for cmmmu * Add higher_is_better flag to submission metric * Add CMMMU dataset to README.md * Add logging and refactor submission file generation in docvqa utils.py * pack docvqa * add traceback to print detailed error * Refactor docvqa_test_aggregate_results to accept additional arguments * Add metric check in evaluator.py and update test.yaml and val.yaml * add common `EvalAIAnswerProcessor` for okvqa, textvqa, vizwizvqa and vqav2 * merge textvqa * textvqa * Modify submission file generation for COCO test results * Update test result storage path * update coco cap file name * Update COCO 2017 Caption dataset name * ferret * Add Ferret dataset * Refactor hb_doc_to_text function to include model-specific prompts * Add IconQA and its subtasks * Refactor image list creation in doc_to_visual function * Add process_results function to default template * Update process_results function in iconqa utils.py * refactor flickr30k * change aggregation function * Fix formatting issues and update logging message * Fix llava can not handle only text question (no visuals) * Fix qwen can not handle no image question (no visuals) * Add fuyu prepare accelerator scripts * refactor mme * naming consistency * aggregation_submissions consistency * flickr30k naming consistency * remove submissions for mme * remove unused submission function * Refactor infovqa_test.yaml and infovqa_val.yaml * Refactor code for improved readability and maintainability * stvqa * remane sqa * Update lmms_eval textcaps files and utils.py * Update default prompt for text captions * Refactor textcaps_aggregation_result function * Add generate_submission_file function and update mathvista_aggregate_results signature * Update nocaps_test.yaml and nocaps_val.yaml * refractor internal_eval * Add internal evaluation datasets * pack multidocvqa * mmvet * Fix gpt eval timeout issue for hallubench, restore load from gpt to avoid re evaluating * Refractor llava wild * Refractor llava-bench-coco * Add JSON file generation for gpt evaluation details * mmmu * Remove MMBench English and Chinese tasks * Remove unnecessary return statement in mmbench_aggregate_test_results function * Fix distributed process group initialization * Update dataset paths and group names in mmbench test configs * Update import statements in cc_utils.py, cn_utils.py, and en_utils.py * Add torch module import * lint * Remove IconQA dataset from README.md * Add Multi-DocVQA and its submodules * Add new datasets and update task names * Refactor flickr_aggregation_result function to accept additional arguments * Add timeout kwargs in Accelerator constructor * Add encoding to be utf-8 for cmmmu * Fix llava try and catch, remove torch.distributed.init in main * Ds prepare script for llava --------- Co-authored-by: JvThunder <[email protected]> Co-authored-by: kcz358 <[email protected]> commit d3dfd94 Author: Li Bo <[email protected]> Date: Tue Feb 27 22:52:07 2024 +0800 [Wandb Logger] add models, and args to wandb tables. (#55) * Refactor logging in lmms_eval package * Refactor variable names in lmms_eval package * Update commands.md * Add repr_scripts for reference * Add timeout for gpt4V * Remove unnecessary dependencies * Add reproduce into readme * Revise seedbench process_result * Fix exclude dc hardcode postprocess logic error * Fix metric repeat issue * Update dataset runtime and add environment info * Revise val submission file saving path * Put the correct query into the gpt extraction * Update sleep time in utils.py * update --------- Co-authored-by: Fanyi Pu <[email protected]> Co-authored-by: kcz358 <[email protected]> Co-authored-by: jzhang38 <[email protected]> Co-authored-by: kcz358 <[email protected]>
- Loading branch information
5 people
authored
Mar 7, 2024
1 parent
9415396
commit 704dd69