mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
edab1c07ba
* 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_gsm8k_agent_gen_be1606.py | ||
| gsm8k_0shot_gen_a58960.py | ||
| gsm8k_0shot_v2_gen_a58960.py | ||
| gsm8k_agent_gen_c3dff3.py | ||
| gsm8k_gen_1d7fe4.py | ||
| gsm8k_gen_1dce88.py | ||
| gsm8k_gen_17d0dc.py | ||
| gsm8k_gen_57b0b1.py | ||
| gsm8k_gen_3309bd.py | ||
| gsm8k_gen_701491.py | ||
| gsm8k_gen_a3e34a.py | ||
| gsm8k_gen_d6de81.py | ||
| gsm8k_gen_e9e91e.py | ||
| gsm8k_gen_ee684f.py | ||
| gsm8k_gen.py | ||
| README.md | ||
GSM8K
python3 run.py --models hf_internlm2_7b --datasets gsm8k_gen_17d0dc --debug
python3 run.py --models hf_internlm2_chat_7b --datasets gsm8k_gen_1d7fe4 --debug
Base Models
| model | gsm8k |
|---|---|
| llama-7b-turbomind | 10.31 |
| llama-13b-turbomind | 20.55 |
| llama-30b-turbomind | 42.08 |
| llama-65b-turbomind | 54.81 |
| llama-2-7b-turbomind | 16.76 |
| llama-2-13b-turbomind | 29.87 |
| llama-2-70b-turbomind | 63.53 |
| llama-3-8b-turbomind | 54.28 |
| llama-3-70b-turbomind | 69.98 |
| internlm2-1.8b-turbomind | 30.40 |
| internlm2-7b-turbomind | 69.98 |
| internlm2-20b-turbomind | 76.80 |
| qwen-1.8b-turbomind | 23.73 |
| qwen-7b-turbomind | 54.36 |
| qwen-14b-turbomind | 61.64 |
| qwen-72b-turbomind | 79.68 |
| qwen1.5-0.5b-hf | 13.27 |
| qwen1.5-1.8b-hf | 34.87 |
| qwen1.5-4b-hf | 47.61 |
| qwen1.5-7b-hf | 54.36 |
| qwen1.5-14b-hf | 63.53 |
| qwen1.5-32b-hf | 72.71 |
| qwen1.5-72b-hf | 79.53 |
| qwen1.5-moe-a2-7b-hf | 61.26 |
| mistral-7b-v0.1-hf | 47.61 |
| mistral-7b-v0.2-hf | 45.19 |
| mixtral-8x7b-v0.1-hf | 66.26 |
| mixtral-8x22b-v0.1-hf | 82.87 |
| yi-6b-hf | 39.58 |
| yi-34b-hf | 67.70 |
| deepseek-7b-base-hf | 20.17 |
| deepseek-67b-base-hf | 68.16 |
Chat Models
| model | gsm8k |
|---|---|
| qwen1.5-0.5b-chat-hf | 8.79 |
| qwen1.5-1.8b-chat-hf | 27.60 |
| qwen1.5-4b-chat-hf | 47.61 |
| qwen1.5-7b-chat-hf | 56.25 |
| qwen1.5-14b-chat-hf | 64.90 |
| qwen1.5-32b-chat-hf | 79.91 |
| qwen1.5-72b-chat-hf | 77.03 |
| qwen1.5-110b-chat-hf | 79.53 |
| internlm2-chat-1.8b-hf | 39.73 |
| internlm2-chat-1.8b-sft-hf | 36.85 |
| internlm2-chat-7b-hf | 69.90 |
| internlm2-chat-7b-sft-hf | 69.83 |
| internlm2-chat-20b-hf | 75.21 |
| internlm2-chat-20b-sft-hf | 76.95 |
| llama-3-8b-instruct-hf | 79.53 |
| llama-3-70b-instruct-hf | 89.76 |
| llama-3-8b-instruct-lmdeploy | 78.77 |
| llama-3-70b-instruct-lmdeploy | 89.31 |
| mistral-7b-instruct-v0.1-hf | 42.23 |
| mistral-7b-instruct-v0.2-hf | 45.56 |
| mixtral-8x7b-instruct-v0.1-hf | 65.13 |