Download evaluation.json from AustinFu/Qev-9B: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/AustinFu/Qev-9B/resolve/main/evaluation.json
- Command line
-
hf download hf://AustinFu/Qev-9B/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/AustinFu/Qev-9B/resolve/main/evaluation.json
1.6 kB
| { | |
| "model": "Qev-9B", | |
| "revision": "v0.2.0", | |
| "full_suite": { | |
| "decision_dev": { | |
| "correct": 1295, | |
| "total": 1468, | |
| "accuracy": 0.8821525885558583, | |
| "rejected": 0 | |
| }, | |
| "transfer_dev": { | |
| "correct": 630, | |
| "total": 764, | |
| "accuracy": 0.824607329842932, | |
| "rejected": 0 | |
| }, | |
| "mmlupro": { | |
| "correct": 574, | |
| "total": 1000, | |
| "accuracy": 0.574, | |
| "rejected": 0 | |
| }, | |
| "semif": { | |
| "correct": 237, | |
| "total": 252, | |
| "accuracy": 0.9404761904761905, | |
| "rejected": 0 | |
| }, | |
| "scienthoon": { | |
| "correct": 620, | |
| "total": 873, | |
| "accuracy": 0.7101947308132875, | |
| "rejected": 0 | |
| }, | |
| "wanli": { | |
| "correct": 182, | |
| "total": 256, | |
| "accuracy": 0.7109375, | |
| "rejected": 0 | |
| }, | |
| "public": { | |
| "correct": 192, | |
| "total": 231, | |
| "accuracy": 0.8311688311688312, | |
| "rejected": 0 | |
| } | |
| }, | |
| "matched_subsets": { | |
| "decision_dev_all": { | |
| "correct": 1295, | |
| "total": 1468 | |
| }, | |
| "decision_dev_clean": { | |
| "correct": 1105, | |
| "total": 1264 | |
| }, | |
| "transfer_dev_all": { | |
| "correct": 630, | |
| "total": 764 | |
| }, | |
| "transfer_dev_clean": { | |
| "correct": 551, | |
| "total": 656 | |
| }, | |
| "mmlupro": { | |
| "correct": 574, | |
| "total": 1000 | |
| }, | |
| "semif_handwritten": { | |
| "correct": 134, | |
| "total": 144 | |
| }, | |
| "scienthoon": { | |
| "correct": 620, | |
| "total": 873 | |
| }, | |
| "wanli": { | |
| "correct": 182, | |
| "total": 256 | |
| }, | |
| "jevbench_public": { | |
| "correct": 192, | |
| "total": 231 | |
| } | |
| } | |
| } | |