Downloads · 30 days
0
ApyHTML19/Qwen2-3B-LoRA-JurisRoute
Qwen2-3B-LoRA-JurisRoute is a machine learning model from ApyHTML19. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
JurisRoute is a fine-tuned version of Qwen2-7B using LoRA (Low-Rank Adaptation) for legal and juridical question answering.
Downloads · 30 days
0
Access
Public
Updated Jun 26, 2026
Repo size
162 MB
Likes
1
Public
Click a slice to open those files.
.safetensors162 MB · 93%
From the Hugging Face model README
JurisRoute is a fine-tuned version of Qwen2-7B using LoRA (Low-Rank Adaptation) for legal and juridical question answering.
The model is specialized for:
The goal of JurisRoute is to provide an accessible AI assistant capable of answering legal questions based on Moroccan juridical texts, without requiring expensive cloud infrastructure.
| Parameter | Value |
|---|---|
| Method | LoRA |
| Rank (r) | 16 |
| Alpha | 32 |
| Target modules | q_proj, v_proj |
| Dropout | 0.05 |
| Parameter | Value |
|---|---|
| Framework | Hugging Face PEFT |
| Precision | FP16 |
| Optimizer | AdamW |
| Dataset | Moroccan legal texts |

