theharshithh commited on
Commit
a086178
·
verified ·
1 Parent(s): 50b73b9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -1,3 +1,10 @@
 
 
 
 
 
 
 
1
  # Speculative Decoding
2
 
3
  This model implements Medusa, an efficient speculative decoding approach that can achieve up to 3x faster inference for large language models. The implementation consists of the base Vicuna-7B model augmented with specialized prediction heads that enable parallel token generation.
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ base_model:
6
+ - lmsys/vicuna-7b-v1.5
7
+ ---
8
  # Speculative Decoding
9
 
10
  This model implements Medusa, an efficient speculative decoding approach that can achieve up to 3x faster inference for large language models. The implementation consists of the base Vicuna-7B model augmented with specialized prediction heads that enable parallel token generation.