Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,22 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- meta-llama/Llama-3.2-1B-Instruct
|
| 7 |
+
library_name: mlx
|
| 8 |
+
tags:
|
| 9 |
+
- llama
|
| 10 |
+
- librarian
|
| 11 |
+
- mlx
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
This is a fine-tuned model of (meta-llama/Llama-3.2-1B-Instruct)[https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct] using MLX on Apple Silicon. The dataset is based on (FinGreyLit)[https://github.com/NatLibFi/FinGreyLit],
|
| 15 |
+
a dataset of Finnish Grey Literature. Only the English articles from the complete FinGreyLit data set were used for training.
|
| 16 |
+
|
| 17 |
+
The model is trained as a Librarian to extract bibliographic information from papers with the system prompt:
|
| 18 |
+
|
| 19 |
+
>"You are a skilled librarian
|
| 20 |
+
>specialized in meticulous cataloguing of digital documents.
|
| 21 |
+
>Extract metadata from this document. Return as JSON."
|
| 22 |
+
|