Commit
•
733075e
1
Parent(s):
8e90e4e
Update README.md
Browse files
README.md
CHANGED
@@ -31,7 +31,8 @@ this model omit the first step from the method described above, and it works.
|
|
31 |
|
32 |
## Using the Model
|
33 |
|
34 |
-
To load the model, a custom `LlamaForCausalLM` is required.
|
|
|
35 |
|
36 |
## References
|
37 |
|
|
|
31 |
|
32 |
## Using the Model
|
33 |
|
34 |
+
To load the model, a custom `LlamaForCausalLM` is required.
|
35 |
+
You can find quantized llama [here](https://github.com/LearnItAnyway/quantized_llama).
|
36 |
|
37 |
## References
|
38 |
|