Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Ashx098
/
Mini-LLM
like
4
Text Generation
Safetensors
PyTorch
English
doi:10.57967/hf/7332
llm
decoder-only
transformer
from-scratch
research
educational
80m
pretraining
custom-architecture
License:
mit
Model card
Files
Files and versions
xet
Community
main
Mini-LLM
/
phase-1-pretraining
/
plots
71.2 kB
1 contributor
History:
1 commit
Ashx098
Upload folder using huggingface_hub
6b16cfb
verified
about 2 months ago
loss_curve.png
31.1 kB
Upload folder using huggingface_hub
about 2 months ago
lr_curve.png
40.1 kB
Upload folder using huggingface_hub
about 2 months ago