Downloads · 30 days
0
ingredient_sub_test
sawnayhtetwin/ingredient_sub_test
ingredient_sub_test is a machine learning model from sawnayhtetwin. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Python 3.8 or higher - CUDA-compatible GPU (recommended for optimal performance) - At least 8GB of RAM (16GB+ recommended)
Access
Public
Updated Aug 7, 2025
Repo size
27.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.3 MB · 87%
At a glance
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025
- SHA
- 96ccebf9
Model card
From the Hugging Face model README
Context-Aware Culinary AI v3 - Interactive Demo
Installation
Prerequisites
- Python 3.8 or higher
- CUDA-compatible GPU (recommended for optimal performance)
- At least 8GB of RAM (16GB+ recommended)
Setup
-
Clone or download this repository
cd ingredient_sub -
Install dependencies
pip install -r requirements.txt
Configuration
The demo uses the following default configuration (in DemoConfig class):
- Base Model:
mistralai/Mistral-7B-v0.1 - Adapter Path:
context_aware_v3_adapter - Max Substitutes: 5
- Max Recipes: 5
- Temperature: 0.3 (controls randomness)
- Top-p: 0.9 (nucleus sampling)
You can modify these settings by editing the DemoConfig class in demo_script.py.
Hardware Requirements
Minimum Requirements
- RAM: 8GB system RAM
- GPU: 4GB VRAM (or CPU-only mode)
- Storage: 15GB free space
- Created
- Aug 7, 2025
- Updated
- Aug 7, 2025