Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
DrNerd
/
LLAMA-3-From-Scratch
like
1
Text Generation
Transformers
Salesforce/wikitext
English
text-generation-inference
custom-code
from-scratch
llama-inspired
educational
wikitext
deepseek-tokenizer
~200M-params
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
LLAMA-3-From-Scratch
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
DrNerd
Updated README.md
37db96e
verified
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
3.93 kB
Updated README.md
2 months ago
inference.py
17.5 kB
Upload 7 files
2 months ago
loss_plot_step_0_to_120.png
59.1 kB
Upload 7 files
2 months ago
model_architecture.py
36.4 kB
Upload 7 files
2 months ago
step_600.pt
2.2 GB
LFS
Upload 7 files
2 months ago
step_800.pt
2.2 GB
LFS
Upload 7 files
2 months ago
wikitext2_tokens_128k.pt
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
7.3 MB
LFS
Upload 7 files
2 months ago
wikitext2_val_tokens_128k.pt
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
761 kB
LFS
Upload 7 files
2 months ago