Add Typed Decisions benchmark results
#2
by codelion - opened
.eval_results/typed-decisions.yaml
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: LocalLLaMA/typed-decisions
|
| 3 |
+
task_id: accuracy
|
| 4 |
+
value: 0.701
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions
|
| 7 |
+
name: Typed Decisions leaderboard (README)
|
| 8 |
+
user: LocalLLaMA
|
| 9 |
+
notes: "General model (any question schema at request time), not fitted by us on this benchmark's train split. Scored on the full 400-case test split (2,000 decisions): one request per case with all five questions, text only, the benchmark's own metrics, MLX on an Apple M3 Max."
|
| 10 |
+
- dataset:
|
| 11 |
+
id: LocalLLaMA/typed-decisions
|
| 12 |
+
task_id: kl_from_gold
|
| 13 |
+
value: 0.2126
|
| 14 |
+
source:
|
| 15 |
+
url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions
|
| 16 |
+
name: Typed Decisions leaderboard (README)
|
| 17 |
+
user: LocalLLaMA
|
| 18 |
+
notes: "General model (any question schema at request time), not fitted by us on this benchmark's train split. Scored on the full 400-case test split (2,000 decisions): one request per case with all five questions, text only, the benchmark's own metrics, MLX on an Apple M3 Max."
|
| 19 |
+
- dataset:
|
| 20 |
+
id: LocalLLaMA/typed-decisions
|
| 21 |
+
task_id: brier
|
| 22 |
+
value: 0.1104
|
| 23 |
+
source:
|
| 24 |
+
url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions
|
| 25 |
+
name: Typed Decisions leaderboard (README)
|
| 26 |
+
user: LocalLLaMA
|
| 27 |
+
notes: "General model (any question schema at request time), not fitted by us on this benchmark's train split. Scored on the full 400-case test split (2,000 decisions): one request per case with all five questions, text only, the benchmark's own metrics, MLX on an Apple M3 Max."
|
| 28 |
+
- dataset:
|
| 29 |
+
id: LocalLLaMA/typed-decisions
|
| 30 |
+
task_id: ece
|
| 31 |
+
value: 0.1204
|
| 32 |
+
source:
|
| 33 |
+
url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions
|
| 34 |
+
name: Typed Decisions leaderboard (README)
|
| 35 |
+
user: LocalLLaMA
|
| 36 |
+
notes: "General model (any question schema at request time), not fitted by us on this benchmark's train split. Scored on the full 400-case test split (2,000 decisions): one request per case with all five questions, text only, the benchmark's own metrics, MLX on an Apple M3 Max."
|