Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,14 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- zh
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
|
9 |
+
# BlockFFN-Small
|
10 |
+
|
11 |
+
This is the original 0.1B BlockFFN checkpoint used in the paper *BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity* for acceleration tests.
|
12 |
+
You can load and use this model simply by using `AutoTokenizer` and `AutoModelForCausalLM`.
|
13 |
+
|
14 |
+
Links: [[Paper](TODO)] [[Codes](https://github.com/thunlp/BlockFFN)]
|