RA-IT-NER-8B

---

RA-IT-NER-8B

Description: The RA-IT-NER-8B model is trained from LLama3-8B using the proposed Retrieval Augmented Instruction Tuning (RA-IT) approach. This model can be used for English Open NER with and without RAG. The training data is the Pile-NER-type presented by UniversalNER.

Check our paper for more information. Check our github repo about how to use the model.

Inference

The template for inference instances is as follows:

<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);"> <strong>Prompting template:</strong><br/> USER: Here are some examples of named entity recognition: <span style="color: #d73a49;">{Fill the NER examples here}</span><br/> ASSISTANT: I’ve read these examples.<br/> USER: Text: <span style="color: #d73a49;">{Fill the input text here}</span><br/> ASSISTANT: I’ve read this text.<br/> USER: What describes <span style="color: #d73a49;">{Fill the entity type here}</span> in the text?<br/> ASSISTANT: <span style="color: #0366d6;">(model's predictions in JSON format)</span><br/> </div>

Note:

• 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 "Text: {input text}" in the "USER" role.
• Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.

License

This model is released under the CC BY-NC 4.0 license. It is primarily used for research purposes.