Instructions to use ruhai-lin/MixerLoop with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ruhai-lin/MixerLoop with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ruhai-lin/MixerLoop", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download legacy/fullloop-42m/eval/core_eval.csv from ruhai-lin/MixerLoop: direct link, hf CLI and curl.
- Browser
- Download file 775 Bytes
-
https://huggingface.co/ruhai-lin/MixerLoop/resolve/main/legacy/fullloop-42m/eval/core_eval.csv
- Command line
-
hf download hf://ruhai-lin/MixerLoop/legacy/fullloop-42m/eval/core_eval.csv
-
curl -L -o core_eval.csv https://huggingface.co/ruhai-lin/MixerLoop/resolve/main/legacy/fullloop-42m/eval/core_eval.csv
775 Bytes
| Task,Accuracy,Centered | |
| hellaswag_zeroshot,0.340669,0.120892 | |
| jeopardy,0.007558,0.007558 | |
| bigbench_qa_wikidata,0.179962,0.179962 | |
| arc_easy,0.480640,0.307520 | |
| arc_challenge,0.248294,-0.002275 | |
| copa,0.450000,-0.100000 | |
| commonsense_qa,0.212121,0.015152 | |
| piqa,0.651251,0.302503 | |
| openbook_qa,0.312000,0.082667 | |
| lambada_openai,0.234232,0.234232 | |
| hellaswag,0.336288,0.115050 | |
| winograd,0.597070,0.194139 | |
| winogrande,0.528019,0.056038 | |
| bigbench_dyck_languages,0.067000,0.067000 | |
| agi_eval_lsat_ar,0.234783,0.043478 | |
| bigbench_cs_algorithms,0.361364,0.361364 | |
| bigbench_operators,0.123810,0.123810 | |
| bigbench_repeat_copy_logic,0.000000,0.000000 | |
| squad,0.059224,0.059224 | |
| coqa,0.099712,0.099712 | |
| boolq,0.586239,-0.088846 | |
| bigbench_language_identification,0.254900,0.180308 | |
| CORE,,0.107249 | |