Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
parrishcorcoran
/
MedusaBitNet-2B-4T
like
0
Text Generation
GGUF
English
bitnet
speculative-decoding
medusa
ternary-weights
efficient-inference
cpu-inference
arxiv:
2401.10774
License:
mit
Model card
Files
Files and versions
xet
Community
main
MedusaBitNet-2B-4T
/
figures
1.78 MB
Ctrl+K
Ctrl+K
2 contributors
History:
1 commit
parrishcorcoran
Upload folder using huggingface_hub
0f4a2f7
verified
3 days ago
architecture.png
163 kB
xet
Upload folder using huggingface_hub
3 days ago
energy_efficiency.png
136 kB
xet
Upload folder using huggingface_hub
3 days ago
head_accuracy.png
189 kB
xet
Upload folder using huggingface_hub
3 days ago
headtohead_throughput.png
119 kB
xet
Upload folder using huggingface_hub
3 days ago
hero_summary.png
122 kB
xet
Upload folder using huggingface_hub
3 days ago
medusa_speedup.png
142 kB
xet
Upload folder using huggingface_hub
3 days ago
memory_vs_energy.png
146 kB
xet
Upload folder using huggingface_hub
3 days ago
performance_summary.png
153 kB
xet
Upload folder using huggingface_hub
3 days ago
pipeline_timeline.png
Safe
51.9 kB
Upload folder using huggingface_hub
3 days ago
quality_vs_efficiency.png
148 kB
xet
Upload folder using huggingface_hub
3 days ago
status_transparency.png
168 kB
xet
Upload folder using huggingface_hub
3 days ago
throughput_vs_quality.png
152 kB
xet
Upload folder using huggingface_hub
3 days ago
training_loss.png
Safe
85.1 kB
Upload folder using huggingface_hub
3 days ago
