Faster Text Generation with Self-Speculative Decoding
•
49
Mostafa Elhoushi
melhoushi
AI & ML interests
Make ML faster, smaller, and more accurate
Recent Activity
updated
a model
4 days ago
melhoushi/exitskip-llama2-7b-topv1-v2
published
a model
4 days ago
melhoushi/exitskip-llama2-7b-topv1-v2
updated
a model
4 days ago
melhoushi/exitskip-llama2-7b-topv1-v1
Articles
Organizations
models
16
melhoushi/exitskip-llama2-7b-topv1-v2
Updated
•
2
melhoushi/exitskip-llama2-7b-topv1-v1
Updated
•
2
melhoushi/layerskip-llama2-7b-topv1-v4
Updated
•
2
melhoushi/layerskip-huggingface-smollm-135m-topv1-v2
Updated
•
2
melhoushi/layerskip-huggingface-smolm-135m-topv1-v1
Updated
•
7
melhoushi/layerskip-llama2-7b-topv1-v3
Updated
•
3
melhoushi/layerskip-facebook-opt125m-topv1-v1
Updated
melhoushi/layerskip-llama2-7b-topv1-v2
Text Generation
•
Updated
•
3
melhoushi/layerskip-llama2-7b-topv1-v1
Text Generation
•
Updated
•
17
melhoushi/layerskip-llama3.2-1b-topv1-v7
Updated
•
3
datasets
None public yet