TMElyralab
/

lyraChatGLM

Model card Files Files and versions Community

vanewu commited on May 15, 2023

Commit

935be87

•

1 Parent(s): 7991465

fixed readme.

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ The inference speed of lyraChatGLM has achieved **10x** acceleration upon the or
 Among its main features are:
 - weights: original ChatGLM-6B weights released by THUDM.
-- device: lyraChatGLM is mainly based on FasterTransformer compiled for SM=80 (A100, for example), but a lot faster.
 - batch_size: compiled with dynamic batch size, max batch_size = 8
 ## Speed

 Among its main features are:
 - weights: original ChatGLM-6B weights released by THUDM.
+- device: lyraChatGLM is mainly based on TensorRT compiled for SM=80 (A100, for example).
 - batch_size: compiled with dynamic batch size, max batch_size = 8
 ## Speed