Downloads · 30 days
11
29% of all-time downloads
nvila-walk-130samples
blind-assist/nvila-walk-130samples
nvila-walk-130samples is a machine learning model from blind-assist. 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.
Fine-tuned NVILA-Lite-2B model for blind assistance navigation.
All-time downloads
38
Public
Repo size
8.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt7.7 GB · 85%
At a glance
- License
- apache-2.0
- Model type
- llava_llama
- Access
- Public
- Created
- Dec 28, 2025
- Updated
- Dec 28, 2025
- SHA
- 91a0b895
Base models
Datasets
Model card
From the Hugging Face model README
nvila-walk-130samples
Fine-tuned NVILA-Lite-2B model for blind assistance navigation.
Model Details
- Base Model: Efficient-Large-Model/NVILA-Lite-2B
- Training Dataset Size: 130 samples
- Train: 91
- Validation: 19
- Test: 20
- Training Date: 2025-12-28
- Run Name: NVILA-2B-Walk-130samples-20251228_200126
Task
Given visual input from a user's forward perspective, generate exactly one short sentence to guide a visually impaired user by:
- Identifying critical obstacles or landmarks
- Describing locations using clock directions (12 o'clock is straight ahead)
- Including relevant details (size, material, distance)
- Giving one clear action
- Prioritizing immediate safety
Example Output
"At 1 o'clock direction there is a tree, be careful to avoid it."
Usage
from llava.model.builder import load_pretrained_model
model_path = "blind-assist/nvila-walk-130samples"
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path)
Training Configuration
- Batch Size: 8 (effective)
- GPUs: 1
- Precision: BF16
- Type
- llava_llama
- License
- apache-2.0
- Created
- Dec 28, 2025
- Updated
- Dec 28, 2025