Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: text-generation
|
3 |
+
inference: true
|
4 |
+
widget:
|
5 |
+
- text: 'Hello!'
|
6 |
+
example_title: Hello world
|
7 |
+
group: Python
|
8 |
+
library_name: transformers
|
9 |
+
---
|
10 |
+
|
11 |
+
# yujiepan/opt-350m-w8a8-unstructured50
|
12 |
+
|
13 |
+
This model is w8a8 quantized & unstructually sparsified by OpenVINO, exported from [facebook/opt-350m](https://huggingface.co/facebook/opt-350m).
|
14 |
+
|
15 |
+
**This model is not tuned for accuracy.**
|
16 |
+
|
17 |
+
- Quantization: 8-bit symmetric for weights & activations
|
18 |
+
- Unstructured sparsity in transformer block linear layers: 50%
|
19 |
+
|
20 |
+
Codes for export: https://gist.github.com/yujiepan-work/1e6dd9f9c2aac0e9ecaf2ed4d82d1158
|