Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- lv
|
| 5 |
+
base_model:
|
| 6 |
+
- meta-llama/Llama-3.1-8B-Instruct
|
| 7 |
+
tags:
|
| 8 |
+
- legal
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
This is a fine-tuned version of the **Llama3.1-8B-Instruct** model, adapted for answering questions about legislation in Latvia. The model was fine-tuned on a [dataset](http://hdl.handle.net/20.500.12574/130) of ~15 thousand question–answer pairs sourced from the [LVportals.lv](https://lvportals.lv/e-konsultacijas) archive.
|
| 12 |
+
|
| 13 |
+
A quantized version of the model is available for use with Ollama or other local LLM runtime environments that support the GGUF format.
|
| 14 |
+
|
| 15 |
+
The data preparation, fine-tuning process, and comprehensive evaluation are described in more detail in:
|
| 16 |
+
|
| 17 |
+
> Artis Pauniņš. Evaluation and Adaptation of Large Language Models for Question-Answering on Legislation. Master’s Thesis. University of Latvia, 2025.
|
| 18 |
+
|
| 19 |
+
**Note**:
|
| 20 |
+
|
| 21 |
+
The model may occasionally generate overly long responses. To prevent this, it is recommended to set the `num_predict` parameter to limit the number of tokens generated - either in your Python code or in the `Modelfile`, depending on how the model is run.
|