Update README.md
Browse files
README.md
CHANGED
|
@@ -12,11 +12,12 @@ base_model:
|
|
| 12 |
- meta-llama/Llama-3.1-8B-Instruct
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# SLIMER-3: Show Less Instruct More Entity Recognition LLaMA3
|
| 16 |
|
| 17 |
-
This LLaMA-3 based model scores +
|
|
|
|
| 18 |
|
| 19 |
-
GitHub repository: https://github.com/andrewzamai/SLIMER
|
| 20 |
|
| 21 |
SLIMER is an LLM specifically instructed for zero-shot NER on English language.
|
| 22 |
|
|
@@ -24,7 +25,6 @@ SLIMER for Italian language can be found at: https://huggingface.co/expertai/LLa
|
|
| 24 |
|
| 25 |
Instructed on a reduced number of samples, it is designed to tackle never-seen-before Named Entity tags by leveraging a prompt enriched with a DEFINITION and GUIDELINES for the NE to be extracted.
|
| 26 |
|
| 27 |
-
|
| 28 |
<!DOCTYPE html>
|
| 29 |
<html>
|
| 30 |
<head>
|
|
|
|
| 12 |
- meta-llama/Llama-3.1-8B-Instruct
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# SLIMER-3-PARALLEL: Show Less Instruct More Entity Recognition LLaMA3
|
| 16 |
|
| 17 |
+
This LLaMA-3 based model scores +17 % over paper's original SLIMER LLaMA-2,
|
| 18 |
+
while allowing up to 16 NEs to be extracted in parallel per prompt.
|
| 19 |
|
| 20 |
+
GitHub repository: https://github.com/andrewzamai/SLIMER/tree/LLaMA3
|
| 21 |
|
| 22 |
SLIMER is an LLM specifically instructed for zero-shot NER on English language.
|
| 23 |
|
|
|
|
| 25 |
|
| 26 |
Instructed on a reduced number of samples, it is designed to tackle never-seen-before Named Entity tags by leveraging a prompt enriched with a DEFINITION and GUIDELINES for the NE to be extracted.
|
| 27 |
|
|
|
|
| 28 |
<!DOCTYPE html>
|
| 29 |
<html>
|
| 30 |
<head>
|