Upload README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ language:
|
|
| 10 |
|
| 11 |
**Description**: The RA-IT-NER-8B model is trained from LLama3-8B using the proposed Retrieval Augmented Instruction Tuning (RA-IT) approach. The training data is the [Pile-NER-type](https://huggingface.co/datasets/Universal-NER/Pile-NER-type) presented by [UniversalNER](https://arxiv.org/abs/2308.03279).
|
| 12 |
|
|
|
|
|
|
|
| 13 |
## Inference
|
| 14 |
The template for inference instances is as follows:
|
| 15 |
<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);">
|
|
|
|
| 10 |
|
| 11 |
**Description**: The RA-IT-NER-8B model is trained from LLama3-8B using the proposed Retrieval Augmented Instruction Tuning (RA-IT) approach. The training data is the [Pile-NER-type](https://huggingface.co/datasets/Universal-NER/Pile-NER-type) presented by [UniversalNER](https://arxiv.org/abs/2308.03279).
|
| 12 |
|
| 13 |
+
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.
|
| 14 |
+
|
| 15 |
## Inference
|
| 16 |
The template for inference instances is as follows:
|
| 17 |
<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);">
|