ENOT-AutoDL
/

gpt-j-6B-tensorrt-int8

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

igor commited on Jun 8, 2023

Commit

2b7d07d

•

1 Parent(s): 8245433

updated metrics table

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ This repository contains GPT-J 6B onnx model suitable for building TensorRT int8
 |   |TensorRT INT8+FP32|torch FP16|torch FP32|
 |---|:---:|:---:|:---:|
-| **Lambada Acc** |78.79%|79.17%|-|
 | **Model size (GB)**  |8.5|12.1|24.2|
 ### Test environment

 |   |TensorRT INT8+FP32|torch FP16|torch FP32|
 |---|:---:|:---:|:---:|
+| **Lambada Acc** |78.46%|79.53%|-|
 | **Model size (GB)**  |8.5|12.1|24.2|
 ### Test environment