EmmaStrong
commited on
Commit
•
94209ab
1
Parent(s):
0118b6a
Upload README.md
Browse files
README.md
CHANGED
@@ -8,13 +8,13 @@ language:
|
|
8 |
|
9 |
# RA-IT-NER-zh-7B
|
10 |
|
11 |
-
**Description**: The RA-IT-NER-zh-7B model is trained from Qwen1.5-7B using the proposed Retrieval Augmented Instruction Tuning (RA-IT) approach. The training data is our constructed [Sky-NER ](https://huggingface.co/datasets/EmmaStrong/Sky-NER), an instruction tuning dataset for Chinese OpenNER. We follow the recipe of [UniversalNER](https://arxiv.org/abs/2308.03279) and use the large-scale [
|
12 |
|
13 |
<div style="background-color: #f6f8fa; padding: 20px; border-radius: 10px; border: 1px solid #e1e4e8; box-shadow: 0 2px 5px rgba(0,0,0,0.1);">
|
14 |
<strong>Instruction:</strong><br/>
|
15 |
给定一段文本,你的任务是抽取所有实体并识别它们的实体类别。输出应为以下JSON格式:[{"实体1": "实体1的类别"}, ...]。</div>
|
16 |
|
17 |
-
|
18 |
|
19 |
## Inference
|
20 |
The template for inference instances is as follows:
|
@@ -32,6 +32,8 @@ Note:
|
|
32 |
* The model can conduct inference **with and without** NER examples. If you want to conduct inference without examples, just start from the third line in the above template by directly inputting "文本:{input text}" in the "USER" role.
|
33 |
* Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
|
34 |
|
|
|
|
|
35 |
## License
|
36 |
|
37 |
This model and its associated data are released under the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) license. They are primarily used for research purposes.
|
|
|
8 |
|
9 |
# RA-IT-NER-zh-7B
|
10 |
|
11 |
+
**Description**: The RA-IT-NER-zh-7B model is trained from Qwen1.5-7B using the proposed Retrieval Augmented Instruction Tuning (RA-IT) approach. The training data is our constructed [Sky-NER ](https://huggingface.co/datasets/EmmaStrong/Sky-NER), an instruction tuning dataset for Chinese OpenNER. We follow the recipe of [UniversalNER](https://arxiv.org/abs/2308.03279) and use the large-scale [SkyPile Corpus](https://huggingface.co/datasets/Skywork/SkyPile-150B) to construct this dataset. The data was collected by prompting gpt-3.5-turbo-0125 to label entities from passages and provide entity tags. The data collection prompt is as follows:
|
12 |
|
13 |
<div style="background-color: #f6f8fa; padding: 20px; border-radius: 10px; border: 1px solid #e1e4e8; box-shadow: 0 2px 5px rgba(0,0,0,0.1);">
|
14 |
<strong>Instruction:</strong><br/>
|
15 |
给定一段文本,你的任务是抽取所有实体并识别它们的实体类别。输出应为以下JSON格式:[{"实体1": "实体1的类别"}, ...]。</div>
|
16 |
|
17 |
+
Check our [paper](todo) for more information. Check our [github repo](https://github.com/Emma1066/Retrieval-Augmented-IT-OpenNER) about how to use the model.
|
18 |
|
19 |
## Inference
|
20 |
The template for inference instances is as follows:
|
|
|
32 |
* The model can conduct inference **with and without** NER examples. If you want to conduct inference without examples, just start from the third line in the above template by directly inputting "文本:{input text}" in the "USER" role.
|
33 |
* Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
|
34 |
|
35 |
+
|
36 |
+
|
37 |
## License
|
38 |
|
39 |
This model and its associated data are released under the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) license. They are primarily used for research purposes.
|