Downloads · 30 days
50
22% of all-time downloads
nanogpt-enwik8-compressed-working
prompterminal/nanogpt-enwik8-compressed-working
nanogpt-enwik8-compressed-working is a text generation model from prompterminal. Use it when you need the model to write or continue text. The card lists the license as mit.
- Performance: 1.635 → 1.637 BPC (+0.002) - Parameters: 28,801,536 → 27,359,744 - Compression: 1.053× smaller (5.0% reduction) - Quality Loss: Only 0.1% degradation!
All-time downloads
231
Public
Repo size
109 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin109 MB · 100%
At a glance
- Task
- Text Generation
- License
- mit
- Model type
- nanogpt_compressed
- Access
- Public
- Created
- Jul 21, 2025
- Updated
- Jul 21, 2025
- SHA
- 255e8486
Try a prompt
Datasets
Model card
From the Hugging Face model README
Compressed nanoGPT (enwik8)
Outstanding Compression Results!
- Performance: 1.635 → 1.637 BPC (+0.002)
- Parameters: 28,801,536 → 27,359,744
- Compression: 1.053× smaller (5.0% reduction)
- Quality Loss: Only 0.1% degradation!
This demonstrates near-perfect compression of a character-level transformer.
Usage
from transformers import AutoModel
model = AutoModel.from_pretrained(
"prompterminal/nanogpt-enwik8-compressed-working",
trust_remote_code=True
)
# Generate text
import torch
prompt = torch.randint(0, 6060, (1, 10)) # Random start
output = model.generate(prompt, max_new_tokens=100)
Research Impact
First successful demonstration of high-quality compression on character-level transformers!
- Task
- Text Generation
- Type
- nanogpt_compressed
- License
- mit
- Created
- Jul 21, 2025
- Updated
- Jul 21, 2025