Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
andrewdalpino
/
LightGPT
like
1
Text Generation
Skylion007/openwebtext
tatsu-lab/alpaca
English
LightGPT
Open-source
License:
apache-2.0
Model card
Files
Files and versions
Community
main
LightGPT
2 contributors
History:
12 commits
Andrew DalPino
Use Fineweb instead of Openwebtext
3325763
about 8 hours ago
dataset
Initial commit
5 days ago
models
Initial commit
5 days ago
out
Initial commit
5 days ago
.gitattributes
Safe
1.52 kB
Initial commit
5 days ago
.gitignore
Safe
128 Bytes
Initial commit
5 days ago
README.md
Safe
12.2 kB
Use Fineweb instead of Openwebtext
about 8 hours ago
beam_search.py
Safe
2.63 kB
Add FSDP
3 days ago
data.py
Safe
7.88 kB
Use Fineweb instead of Openwebtext
about 8 hours ago
generate.py
Safe
2.62 kB
Initial commit
5 days ago
instruction-tune.py
Safe
5.66 kB
Add MFU estimation for Ampere GPUs
1 day ago
model.py
Safe
14.5 kB
Add MFU estimation for Ampere GPUs
1 day ago
model_sizing.ipynb
Safe
69.5 kB
Use Fineweb instead of Openwebtext
about 8 hours ago
pre-train.py
Safe
10.7 kB
Use Fineweb instead of Openwebtext
about 8 hours ago
requirements.txt
Safe
109 Bytes
Initial commit
5 days ago
