kuotient
/

Llama-3-11B-Instruct-attenuated

Text Generation

text-generation-inference

Model card Files Files and versions

kuotient commited on Apr 20, 2024

Commit

a04f489

·

verified ·

1 Parent(s): 1dc1e5a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -86,5 +86,5 @@ slices:
       layer_range: [24, 32] # The last 8 layers of Block 3 are not duplicated
 merge_method: passthrough
-dtype: float16
 ```

       layer_range: [24, 32] # The last 8 layers of Block 3 are not duplicated
 merge_method: passthrough
+dtype: bfloat16
 ```