Downloads · 30 days
2
2% of all-time downloads
pythia-160m-minipile_k440_density-proportioned
Marcus2112/pythia-160m-minipile_k440_density-proportioned
pythia-160m-minipile_k440_density-proportioned is a machine learning model from Marcus2112. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
107
Public
Parameters
162M
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt3.2 GB · 71%
At a glance
- Model type
- gpt_neox
- Access
- Public
- Created
- Dec 16, 2024
- Updated
- Jan 17, 2025
- SHA
- 77041dab
Base models
Model card
From the Hugging Face model README
| Benchmark | Measure | 160M MiniPile | 160M k440 Density | |
|---|---|---|---|---|
| ARC-Challenge | acc | ↑ | 0.2125 ± 0.0120 | 0.1928 ± 0.0115 |
| MMLU | acc | ↑ | 0.2699 ± 0.0037 | 0.2295 ± 0.0035 |
| HellaSwag | acc | ↑ | 0.2560 ± 0.0044 | 0.2603 ± 0.0044 |
| WinoGrande | acc | ↑ | 0.4720 ± 0.0140 | 0.4941 ± 0.0141 |
| Lambada (OpenAI) | acc | ↑ | 0.0000 ± 0.0000 | 0.0000 ± 0.0000 |
| Lambada (OpenAI) | perplexity | ↓ | 3033175.2693 ± 288926.5827 | 2025523.7766 ± 164221.8893 |
| Lambada (Std) | acc | ↑ | 0.0000 ± 0.0000 | 0.0000 ± 0.0000 |
| Lambada (Std) | perplexity | ↓ | 27067951.3460 ± 2710040.191 | 12959844.9407 ± 1160155.0647 |
| BLiMP | acc | ↑ | 0.5194 ± 0.0018 | 0.5520 ± 0.0017 |
- Type
- gpt_neox
- Languages
- en
- Created
- Dec 16, 2024
- Updated
- Jan 17, 2025