|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- lambada |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- text-generation-inference |
|
- causal-lm |
|
- int8 |
|
- tensorrt |
|
- ENOT-AutoDL |
|
--- |
|
|
|
# GPT2 |
|
|
|
This repository contains GPT2 onnx models compatible with TensorRT: |
|
* gpt2-xl.onnx - GPT2-XL onnx for fp32 or fp16 engines |
|
* gpt2-xl-i8.onnx - GPT2-XL onnx for int8+fp32 engines |
|
|
|
Quantization of models was performed by the [ENOT-AutoDL](https://pypi.org/project/enot-autodl/) framewor. |
|
Code for building of TensorRT engines and examples published on [github](https://github.com/ENOT-AutoDL/ENOT-transformers). |
|
|
|
## Metrics: |
|
|
|
### GPT2-XL |
|
|
|
| |TensorRT INT8+FP32|torch FP16| |
|
|---|:---:|:---:| |
|
| **Lambada Acc** |72.11%|71.43%| |
|
|
|
### Test environment |
|
|
|
* GPU RTX 4090 |
|
* CPU 11th Gen Intel(R) Core(TM) i7-11700K |
|
* TensorRT 8.5.3.1 |
|
* pytorch 1.13.1+cu116 |
|
|
|
## Latency: |
|
|
|
### GPT2-XL |
|
|
|
|Input sequance length|Number of generated tokens|TensorRT INT8+FP32 ms|torch FP16 ms|Acceleration| |
|
|:---:|:---:|:---:|:---:|:---:| |
|
|64|64|462|1190|2.58| |
|
|64|128|920|2360|2.54| |
|
|64|256|1890|4710|2.54| |
|
|
|
### Test environment |
|
|
|
* GPU RTX 4090 |
|
* CPU 11th Gen Intel(R) Core(TM) i7-11700K |
|
* TensorRT 8.5.3.1 |
|
* pytorch 1.13.1+cu116 |
|
|
|
## How to use |
|
|
|
Example of inference and accuracy test [published on github](https://github.com/ENOT-AutoDL/ENOT-transformers): |
|
```shell |
|
git clone https://github.com/ENOT-AutoDL/ENOT-transformers |
|
``` |
|
|
