MengniWang
commited on
Commit
•
17b85b7
1
Parent(s):
6d4600d
add model card
Browse files
README.md
CHANGED
@@ -1,3 +1,39 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- lambada
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: transformers
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
tags:
|
10 |
+
- text-generation-inference
|
11 |
+
- causal-lm
|
12 |
+
- int8
|
13 |
+
- ONNX
|
14 |
+
- PostTrainingDynamic
|
15 |
+
- Intel® Neural Compressor
|
16 |
+
- neural-compressor
|
17 |
---
|
18 |
+
|
19 |
+
# INT8 GPT-J 6B
|
20 |
+
|
21 |
+
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.
|
22 |
+
|
23 |
+
This int8 ONNX model is generated by [neural-compressor](https://github.com/intel/neural-compressor) and the fp32 model is from this [repo](https://huggingface.co/OWG/gpt-j-6B).
|
24 |
+
|
25 |
+
## Test result
|
26 |
+
|
27 |
+
| |INT8|FP32|
|
28 |
+
|---|:---:|:---:|
|
29 |
+
| **Model size (GB)** |13|23|
|
30 |
+
|
31 |
+
|
32 |
+
## How to use
|
33 |
+
|
34 |
+
Download the model and script by cloning the repository:
|
35 |
+
```shell
|
36 |
+
git clone https://huggingface.co/Intel/gpt-j-6B-int8-dynamic`
|
37 |
+
```
|
38 |
+
|
39 |
+
Then you can do inference based on the model and script 'evaluation.ipynb'.
|