How to use from
Unsloth StudioInstall Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ivanasp/Llama-3.2-1B-JSON-Extractor to start chattingUsing HuggingFace Spaces for Unsloth
# No setup required# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ivanasp/Llama-3.2-1B-JSON-Extractor to start chattingLoad model with FastModel
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="ivanasp/Llama-3.2-1B-JSON-Extractor",
max_seq_length=2048,
)Quick Links
🚀 Llama-3.2-1B-JSON-Extractor
This model is a professional fine-tuned version of Llama 3.2 1B Instruct, specialized in converting Natural Language into structured JSON objects.
🎯 Project Goal
The system interprets human intent and extracts key entities into a machine-readable format. It is designed to be the bridge between human communication and database systems.
Extracted Fields:
product: Name or description of the item.price: Numerical value (currency independent).category: Market segment or classification.
🛠️ Technical Specifications
- Architecture: Llama 3.2 1B
- Optimization: QLoRA (4-bit)
- Rank (r): 16
- Alpha: 32
- Learning Rate: 2e-4
- Final Training Loss: ~0.013 (High precision)
💡 Usage Example
Input:
"I want to sell a Sony PlayStation 5 for 500 dollars in the gaming category."
Output:
{
"product": "Sony PlayStation 5",
"price": 500,
"category": "gaming"
}
Developed by ivanasp using Unsloth.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install Unsloth Studio (macOS, Linux, WSL)
# Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ivanasp/Llama-3.2-1B-JSON-Extractor to start chatting