Add link to paper and GitHub repository
Browse filesThis PR adds a link to the paper in the introduction and to the GitHub repository to the model card, so people can easily navigate to the paper for more info on the model and code.
README.md
CHANGED
@@ -1,16 +1,17 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
datasets:
|
4 |
- inclusionAI/Ling-Coder-SyntheticQA
|
5 |
language:
|
6 |
- en
|
7 |
- zh
|
8 |
-
pipeline_tag: text-generation
|
9 |
library_name: transformers
|
|
|
|
|
10 |
tags:
|
11 |
- code
|
12 |
- moe
|
13 |
---
|
|
|
14 |
# Ling-Coder-lite-base
|
15 |
|
16 |
<p align="center">
|
@@ -25,7 +26,7 @@ tags:
|
|
25 |
|
26 |
## Introduction
|
27 |
|
28 |
-
Ling-Coder-Lite is a MoE LLM provided and open-sourced by InclusionAI, which has 16.8 billion parameters with 2.75 billion activated parameters. Ling-Coder-Lite performs impressively on coding tasks compared to existing models in the industry. Specifically, Ling-Coder-Lite further pre-training from an intermediate checkpoint of Ling-Lite, incorporating an additional 3 trillion tokens. This extended pre-training significantly boosts the coding abilities of Ling-Lite, while preserving its strong performance in general language tasks.
|
29 |
|
30 |
## Model Downloads
|
31 |
|
@@ -105,4 +106,4 @@ This code repository is licensed under [the MIT License](https://huggingface.co/
|
|
105 |
primaryClass={cs.LG},
|
106 |
url={https://arxiv.org/abs/2503.17793},
|
107 |
}
|
108 |
-
```
|
|
|
1 |
---
|
|
|
2 |
datasets:
|
3 |
- inclusionAI/Ling-Coder-SyntheticQA
|
4 |
language:
|
5 |
- en
|
6 |
- zh
|
|
|
7 |
library_name: transformers
|
8 |
+
license: mit
|
9 |
+
pipeline_tag: text-generation
|
10 |
tags:
|
11 |
- code
|
12 |
- moe
|
13 |
---
|
14 |
+
|
15 |
# Ling-Coder-lite-base
|
16 |
|
17 |
<p align="center">
|
|
|
26 |
|
27 |
## Introduction
|
28 |
|
29 |
+
Ling-Coder-Lite is a MoE LLM provided and open-sourced by InclusionAI, which has 16.8 billion parameters with 2.75 billion activated parameters. Ling-Coder-Lite performs impressively on coding tasks compared to existing models in the industry. Specifically, Ling-Coder-Lite further pre-training from an intermediate checkpoint of Ling-Lite, incorporating an additional 3 trillion tokens. This extended pre-training significantly boosts the coding abilities of Ling-Lite, while preserving its strong performance in general language tasks. This model is described in the paper [Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM](https://huggingface.co/papers/2503.17793).
|
30 |
|
31 |
## Model Downloads
|
32 |
|
|
|
106 |
primaryClass={cs.LG},
|
107 |
url={https://arxiv.org/abs/2503.17793},
|
108 |
}
|
109 |
+
```
|