Benchmark Measure 160M MiniPile 160M Density Tiny Percentage Difference in Means
ARC-Challenge acc 0.2125 ± 0.0120 0.1843 ± 0.0113 -13.2706
MMLU acc 0.2699 ± 0.0037 0.2295 ± 0.0035 -14.9685
HellaSwag acc 0.2560 ± 0.0044 0.2598 ± 0.0044 1.4844
WinoGrande acc 0.4720 ± 0.0140 0.4980 ± 0.0141 5.5085
Lambada (OpenAI) acc 0.0000 ± 0.0000 0.0000 ± 0.0000 -
Lambada (OpenAI) perplexity 3033175.2693 ± 288926.5827 1934160.4021 ± 153855.8657 -36.2331
Lambada (Std) acc 0.0000 ± 0.0000 0.0000 ± 0.0000 -
Lambada (Std) perplexity 27067951.3461 ± 2710040.1910 10354382.8435 ± 900493.0078 -61.7467
BLiMP acc 0.5194 ± 0.0018 0.5363 ± 0.0016 3.2538
Downloads last month
7
Safetensors
Model size
162M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for Marcus2112/pythia-160m-minipile_tiny_density-proportioned

Finetuned
(123)
this model

Dataset used to train Marcus2112/pythia-160m-minipile_tiny_density-proportioned

Collection including Marcus2112/pythia-160m-minipile_tiny_density-proportioned