Downloads · 30 days
2
4% of all-time downloads
pythia-160m-minipile_density_pico_epochs
Marcus2112/pythia-160m-minipile_density_pico_epochs
pythia-160m-minipile_density_pico_epochs 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
51
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
- Jan 14, 2025
- Updated
- Jan 17, 2025
- SHA
- b53ce9e3
Base models
Model card
From the Hugging Face model README
| Benchmark | Measure | 160M Density Pico | 160M Density Pico 2 Epochs | 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 | ↑ | 0.2583 ± 0.0044 | 0.2573 ± 0.0044 | -0.3871 |
| WinoGrande | acc | ↑ | 0.4957 ± 0.0141 | 0.4933 ± 0.0141 | -0.4842 |
| Lambada (OpenAI) | acc | ↑ | 0.0000 ± 0.0000 | 0.0000 ± 0.0000 | - |
| Lambada (OpenAI) | perplexity | ↓ | 1964196.9255 ± 153419.7846 | 2017680.7049 ± 159090.0606 | 2.7229 |
| Lambada (Std) | acc | ↑ | 0.0000 ± 0.0000 | 0.0000 ± 0.0000 | - |
| Lambada (Std) | perplexity | ↓ | 10720344.5522 ± 925236.7038 | 10465698.6884 ± 903166.5195 | -2.3754 |
| BLiMP | acc | ↑ | 0.5383 ± 0.0017 | 0.5405 ± 0.0017 | 0.4087 |
- Type
- gpt_neox
- Languages
- en
- Created
- Jan 14, 2025
- Updated
- Jan 17, 2025