Faster Text Generation with Self-Speculative Decoding
•
47
Mostafa Elhoushi
melhoushi
AI & ML interests
Make ML faster, smaller, and more accurate
Recent Activity
updated
a model
about 4 hours ago
melhoushi/layerskip-llama2-7b-topv1-v1
updated
a model
about 5 hours ago
melhoushi/layerskip-llama3.2-1b-topv1-v7
published
a model
about 6 hours ago
melhoushi/layerskip-llama3.2-1b-topv1-v7
Articles
Organizations
models
8
melhoushi/layerskip-llama2-7b-topv1-v1
Updated
melhoushi/layerskip-llama3.2-1b-topv1-v7
Updated
melhoushi/layerskip-llama3.2-1b-topv1-v6
Updated
melhoushi/layerskip-llama3.2-1b-topv1-v5
Updated
melhoushi/layerskip-llama3.2-1b-topv1-v4
Updated
•
2
melhoushi/layerskip-llama3.2-1b-topv1-v3
Updated
•
4
melhoushi/layerskip-llama3.2-1b-topv1-v2
Updated
•
12
melhoushi/layerskip-llama3.2-1b-topv1-v1
Updated
•
55
datasets
None public yet