Commit
•
b906bb5
1
Parent(s):
b73c089
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ license: llama2
|
|
| 4 |
|
| 5 |
## Description
|
| 6 |
|
| 7 |
-
This model is intended to be used as an accelerator for llama 13B (chat) and takes inspiration
|
| 8 |
from the Medusa architecture and modifies the MLP into a multi-stage MLP, where each stage predicts
|
| 9 |
a single token in the draft. Each stage takes as input both a state vector and sampled token embedding
|
| 10 |
from the prior stage (the base model can be considered stage 0). The inputs are projected and passed
|
|
|
|
| 4 |
|
| 5 |
## Description
|
| 6 |
|
| 7 |
+
This model is intended to be used as an accelerator for [llama 13B (chat)](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) and takes inspiration
|
| 8 |
from the Medusa architecture and modifies the MLP into a multi-stage MLP, where each stage predicts
|
| 9 |
a single token in the draft. Each stage takes as input both a state vector and sampled token embedding
|
| 10 |
from the prior stage (the base model can be considered stage 0). The inputs are projected and passed
|