mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
![]() * add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * udpate dataset for modelscope support * update readme * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * update readme * remove tydiqa japanese subset * add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * update readme * udpate dataset for modelscope support * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * remove tydiqa japanese subset * update util * remove .DS_Store * fix md format * move util into package * update docs/get_started.md * restore eval_api_zhipu_v2.py, add environment setting * Update dataset * Update * Update * Update * Update --------- Co-authored-by: Yun lin <yunlin@U-Q9X2K4QV-1904.local> Co-authored-by: Yunnglin <mao.looper@qq.com> Co-authored-by: Yun lin <yunlin@laptop.local> Co-authored-by: Yunnglin <maoyl@smail.nju.edu.cn> Co-authored-by: zhangsongyang <zhangsongyang@pjlab.org.cn> |
||
---|---|---|
.. | ||
deprecated_humaneval_gen_4a6eef.py | ||
deprecated_humaneval_gen_6d1cc2.py | ||
deprecated_humaneval_gen_a82cae.py | ||
deprecated_humaneval_gen_d2537e.py | ||
deprecated_humaneval_gen_fd5822.py | ||
deprecated_humaneval_gen_ff7054.py | ||
humaneval_gen_8e312c.py | ||
humaneval_gen_66a7f4.py | ||
humaneval_gen.py | ||
humaneval_openai_sample_evals_gen_159614.py | ||
humaneval_passk_gen_8e312c.py | ||
humaneval_repeat10_gen_8e312c.py | ||
README.md |
HumanEval
python3 run.py --models hf_internlm2_7b --datasets deprecated_humaneval_gen_d2537e --debug
python3 run.py --models hf_internlm2_chat_7b --datasets humaneval_gen_8e312c --debug
Base Models
model | pass@1 |
---|---|
llama-7b-turbomind | 12.80 |
llama-13b-turbomind | 15.24 |
llama-30b-turbomind | 9.15 |
llama-65b-turbomind | 7.32 |
llama-2-7b-turbomind | 14.02 |
llama-2-13b-turbomind | 15.24 |
llama-2-70b-turbomind | 15.24 |
llama-3-8b-turbomind | 28.05 |
llama-3-70b-turbomind | 28.05 |
internlm2-1.8b-turbomind | 30.49 |
internlm2-7b-turbomind | 48.17 |
internlm2-20b-turbomind | 51.83 |
qwen-1.8b-turbomind | 16.46 |
qwen-7b-turbomind | 23.78 |
qwen-14b-turbomind | 23.78 |
qwen-72b-turbomind | 66.46 |
qwen1.5-0.5b-hf | 8.54 |
qwen1.5-1.8b-hf | 23.17 |
qwen1.5-4b-hf | 41.46 |
qwen1.5-7b-hf | 53.05 |
qwen1.5-14b-hf | 57.32 |
qwen1.5-32b-hf | 70.12 |
qwen1.5-72b-hf | 65.85 |
qwen1.5-moe-a2-7b-hf | 45.73 |
mistral-7b-v0.1-hf | 14.02 |
mistral-7b-v0.2-hf | 9.15 |
mixtral-8x7b-v0.1-hf | 24.39 |
mixtral-8x22b-v0.1-hf | 16.46 |
yi-6b-hf | 14.63 |
yi-34b-hf | 17.07 |
deepseek-7b-base-hf | 18.29 |
deepseek-67b-base-hf | 23.17 |
Chat Models
model | pass@1 |
---|---|
qwen1.5-0.5b-chat-hf | 9.15 |
qwen1.5-1.8b-chat-hf | 15.85 |
qwen1.5-4b-chat-hf | 30.49 |
qwen1.5-7b-chat-hf | 40.85 |
qwen1.5-14b-chat-hf | 50.00 |
qwen1.5-32b-chat-hf | 57.93 |
qwen1.5-72b-chat-hf | 60.37 |
qwen1.5-110b-chat-hf | 65.24 |
internlm2-chat-1.8b-hf | 33.54 |
internlm2-chat-1.8b-sft-hf | 34.15 |
internlm2-chat-7b-hf | 56.71 |
internlm2-chat-7b-sft-hf | 61.59 |
internlm2-chat-20b-hf | 67.68 |
internlm2-chat-20b-sft-hf | 67.68 |
llama-3-8b-instruct-hf | 55.49 |
llama-3-70b-instruct-hf | 70.73 |
llama-3-8b-instruct-lmdeploy | 57.93 |
llama-3-70b-instruct-lmdeploy | 70.73 |
mistral-7b-instruct-v0.1-hf | 32.32 |
mistral-7b-instruct-v0.2-hf | 29.27 |
mixtral-8x7b-instruct-v0.1-hf | 34.15 |