Downloads · 30 days
0
dylanhogg/gnaf-structured-address-v0.1-75a1791-20250921-063650
gnaf-structured-address-v0.1-75a1791-20250921-063650 is a text generation model from dylanhogg. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as other.
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the gnaf-2022-structured-training-100000-v0-instruct-train dataset.
Downloads · 30 days
0
Access
Public
Updated Oct 18, 2025
Parameters
1.2B
2.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors2.5 GB · 99%
From the Hugging Face model README
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the gnaf-2022-structured-training-100000-v0-instruct-train dataset.
Extracts structured address information from text. Structured output is json with G-NAF (Geocoded National Address File) fields.
Example:
Input text: Lvl 15/333 George St Sydney NSW 2000
Response: {"level_type": "level", "level_number": "15", "street_name": "george", "street_type_code": "street", "locality_name": "sydney", "state_abbreviation": "nsw", "postcode": "2000"}
Note that this model is a work in progresss as of Oct 2025.
More information needed
More information needed
The following hyperparameters were used during training: