Benchmark Measure 1.4B MiniPile 1.4B Reproduction Percentage Difference in Means
ARC-Challenge acc 0.1903 ± 0.0115 0.1928 ± 0.0115 1.3137
MMLU acc 0.2295 ± 0.0035 0.2295 ± 0.0035 0.0000
HellaSwag acc 0.2579 ± 0.0044 0.2584 ± 0.0044 0.1939
WinoGrande acc 0.5185 ± 0.0140 0.5091 ± 0.0141 -1.8129
Lambada (OpenAI) acc 0.0000 ± 0.0000 0.0000 ± 0.0000 -
Lambada (OpenAI) perplexity 1564928.5258 ± 118691.4565 1520707.8702 ± 115261.3664 -2.8257
Lambada (Std) acc 0.0000 ± 0.0000 0.0000 ± 0.0000 -
Lambada (Std) perplexity 8848600.9409 ± 745031.8900 8651201.8876 ± 735161.5236 -1.5685
BLiMP acc 0.5483 ± 0.0017 0.5397 ± 0.0016 -2.2309
ARC-Easy acc 0.2715 ± 0.0091 0.2673 ± 0.0091 -1.5470
Downloads last month
8
Safetensors
Model size
1.41B 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-1.4b-minipile_reproduction

Finetuned
(28)
this model

Dataset used to train Marcus2112/pythia-1.4b-minipile_reproduction

Collection including Marcus2112/pythia-1.4b-minipile_reproduction