Download evaluation/gpu-final-console-metrics.json from karmx/TinyQuery-140M: direct link, hf CLI and curl.
- Browser
- Download file 2.03 kB
-
https://huggingface.co/karmx/TinyQuery-140M/resolve/main/evaluation/gpu-final-console-metrics.json
- Command line
-
hf download hf://karmx/TinyQuery-140M/evaluation/gpu-final-console-metrics.json
-
curl -L -o gpu-final-console-metrics.json https://huggingface.co/karmx/TinyQuery-140M/resolve/main/evaluation/gpu-final-console-metrics.json
2.03 kB
| { | |
| "checkpoint_sha256": "9489b5cde69c11f64b3e7031182e8248aa83790f1ad4aeefbf99a4e5e152e692", | |
| "frozen_at_utc": "2026-09-10T14:00:36.513800+00:00", | |
| "device": "CUDA BF16", | |
| "source": "Completed remote CUDA evaluation; raw GPU predictions were retrieved after SSH access recovered. Independent Mac FP32 evaluation matches all aggregate metrics.", | |
| "decoding": "raw greedy; no repair, constrained decoding or teacher fallback", | |
| "metrics": { | |
| "test": { | |
| "json_valid": { | |
| "correct": 1196, | |
| "total": 1196, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 1191, | |
| "total": 1196, | |
| "rate": 0.995819397993311 | |
| }, | |
| "action_correct": { | |
| "correct": 1192, | |
| "total": 1196, | |
| "rate": 0.9966555183946488 | |
| }, | |
| "tool_correct": { | |
| "correct": 1088, | |
| "total": 1100, | |
| "rate": 0.9890909090909091 | |
| }, | |
| "arguments_exact": { | |
| "correct": 1014, | |
| "total": 1100, | |
| "rate": 0.9218181818181819 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 896, | |
| "total": 912, | |
| "rate": 0.9824561403508771 | |
| }, | |
| "success": { | |
| "correct": 1106, | |
| "total": 1196, | |
| "rate": 0.9247491638795987 | |
| } | |
| }, | |
| "manual": { | |
| "json_valid": { | |
| "correct": 160, | |
| "total": 160, | |
| "rate": 1.0 | |
| }, | |
| "schema_valid": { | |
| "correct": 159, | |
| "total": 160, | |
| "rate": 0.99375 | |
| }, | |
| "action_correct": { | |
| "correct": 159, | |
| "total": 160, | |
| "rate": 0.99375 | |
| }, | |
| "tool_correct": { | |
| "correct": 146, | |
| "total": 152, | |
| "rate": 0.9605263157894737 | |
| }, | |
| "arguments_exact": { | |
| "correct": 124, | |
| "total": 152, | |
| "rate": 0.8157894736842105 | |
| }, | |
| "sql_equivalent": { | |
| "correct": 94, | |
| "total": 112, | |
| "rate": 0.8392857142857143 | |
| }, | |
| "success": { | |
| "correct": 132, | |
| "total": 160, | |
| "rate": 0.825 | |
| } | |
| } | |
| } | |
| } |