VLGuard
by ys-zong
[ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
AI summary
Safety fine-tuner
Improves safety and helpfulness of large language models by fine-tuning them using safety-critical tasks
- stars
- 47
- forks
- 2
- watching
- 3
Similar projects
Found by comparing what the projects do, not just their names.
roboflow/maestro1.4K
fine-tuner
A tool to streamline fine-tuning of multimodal models for vision-language tasks
Learning benchmark
A benchmarking suite for multimodal in-context learning models
Visual Instruction Tuning Tool
A tool for generating and evaluating multimodal Large Language Models with visual instruction tuning capabilities
Model value alignment
Evaluates and aligns the values of Chinese large language models with safety and responsibility standards
Behavior alignment tool
Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy.
Vision model safety test
A benchmark for evaluating the safety and robustness of vision language models against adversarial attacks.
Model debiasing
Debiasing techniques to minimize hallucinations in large visual language models
VLIT model toolkit
A comprehensive dataset and evaluation framework for Vision-Language Instruction Tuning models
Chinese language model fine-tuning tool
Improves pre-trained Chinese language models by incorporating a correction task to alleviate inconsistency issues with downstream tasks
Model validator
Analyzing and mitigating object hallucination in large vision-language models to improve their accuracy and reliability.
Model fine-tuner
Provides guidance on fine-tuning pre-trained models for image classification tasks using PyTorch.
Safe RL Benchmark
A unified benchmark for safe reinforcement learning algorithms and environments.
Multimodal alignment model
Extending pretraining models to handle multiple modalities by aligning language and video representations
LLaMA fine tuner
A Chinese finance-focused large language model fine-tuning framework
Chinese language model
Trains a large Chinese language model on massive data and provides a pre-trained model for downstream tasks
