update docs
Browse files
README.md
CHANGED
@@ -1,3 +1,26 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
license: gpl-3.0
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
# LingLong (玲珑): A Small-Scale Chinese PreTrained Language Model
|
9 |
+
|
10 |
+
This is LingLong (玲珑), a Chinese pretrained language model trained by the College of Software at Nankai University.
|
11 |
+
Built on the foundation of the GPT-3 architecture, it has been meticulously trained on a vast collection of private
|
12 |
+
datasets.
|
13 |
+
With a modest parameter count of only 317 million, LingLong is significantly smaller than the original GPT-3 model, yet
|
14 |
+
it delivers impressive results across various NLP tasks.
|
15 |
+
In Chinese, "玲珑" translates to "exquisite" or "delicate," which perfectly embodies the small yet mighty nature of this
|
16 |
+
model.
|
17 |
+
Therefore, we chose to name it "LingLong" in honor of its exceptional precision and finesse.
|
18 |
+
|
19 |
+
Although it's true that this model's performance isn't on par with the large pretrained language models boasting
|
20 |
+
hundreds of billions of parameters, its relatively low parameter count makes it accessible to researchers with limited
|
21 |
+
computing resources.
|
22 |
+
As a result, this model serves as an excellent foundation for conducting follow-up research, such as fine-tuning.
|
23 |
+
By utilizing this model, researchers can begin to delve into the intricacies of pretrained language models and to
|
24 |
+
unravel the mysteries of language processing without the need for excessive computational resources.
|
25 |
+
|
26 |
+
This is the chat version of [LingLong-317M](https://huggingface.co/AlumiK/LingLong-317M)
|