Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
andrewdalpino
/
LightGPT
like
2
Text Generation
PyTorch
TensorBoard
ONNX
Safetensors
HuggingFaceFW/fineweb
HuggingFaceTB/smoltalk
English
NoPE
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
f4f6bf0
LightGPT
2 contributors
History:
14 commits
Andrew DalPino
Compensate for git issues
f4f6bf0
22 days ago
checkpoints
Compensate for git issues
22 days ago
datasets
Compensate for git issues
22 days ago
out
Initial commit
about 1 month ago
.gitattributes
1.52 kB
Initial commit
about 1 month ago
.gitignore
128 Bytes
Initial commit
about 1 month ago
README.md
12.9 kB
Broad improvements
24 days ago
beam_search.py
2.92 kB
Broad improvements
24 days ago
data.py
7.51 kB
Broad improvements
24 days ago
generate.py
2.9 kB
Broad improvements
24 days ago
instruction-tune.py
6.17 kB
Broad improvements
24 days ago
model.py
14.5 kB
Add MFU estimation for Ampere GPUs
27 days ago
model_sizing.ipynb
69.5 kB
Use Fineweb instead of Openwebtext
25 days ago
pre-train.py
11.1 kB
Broad improvements
24 days ago
requirements.txt
109 Bytes
Initial commit
about 1 month ago