|
--- |
|
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 |
|
--- |
|
|
|
# INT8 GPT-J 6B |
|
|
|
GPT-J 6B is a transformer model trained using Ben Wang's [Mesh Transformer JAX](https://github.com/kingoflolz/mesh-transformer-jax/). "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters. |
|
|
|
This repository contains TensorRT engines with mixed precission int8 + fp32. You can find prebuilt engines for the following GPUs: |
|
* RTX 4090 |
|
* RTX 3080 Ti |
|
* RTX 2080 Ti |
|
|
|
ONNX model generated by [ENOT-AutoDL](https://pypi.org/project/enot-autodl/) and will be published soon. |
|
|
|
## Test result |
|
|
|
| |INT8|FP32| |
|
|---|:---:|:---:| |
|
| **Lambada Acc** |78.50%|79.54%| |
|
| **Model size (GB)** |8.5|24.2| |
|
|
|
|
|
## How to use |
|
|
|
Example of inference and accuracy test published on github: |
|
```shell |
|
git clone https://github.com/ENOT-AutoDL/demo-gpt-j-6B-tensorrt-int8 |
|
``` |
|
|
