VLGuard
Safety fine-tuner
Improves safety and helpfulness of large language models by fine-tuning them using safety-critical tasks
[ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
45 stars
3 watching
1 forks
Language: Python
last commit: 3 months ago alignmentlarge-language-modelslarge-vision-language-modelssafetyvision-language-model
Related projects:
| Repository | Description | Stars |
|---|---|---|
 roboflow/maestro | A tool to streamline fine-tuning of multimodal models for vision-language tasks | 1,386 |
| ys-zong/vl-icl | A benchmarking suite for multimodal in-context learning models | 28 |
 icoz69/stablellava | A tool for generating and evaluating multimodal Large Language Models with visual instruction tuning capabilities | 91 |
 x-plug/cvalues | Evaluates and aligns the values of Chinese large language models with safety and responsibility standards | 477 |
 rlhf-v/rlhf-v | Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy. | 233 |
 ucsc-vlaa/vllm-safety-benchmark | A benchmark for evaluating the safety and robustness of vision language models against adversarial attacks. | 67 |
 yfzhang114/llava-align | Debiasing techniques to minimize hallucinations in large visual language models | 71 |
 liaoning97/revo-lion | A comprehensive dataset and evaluation framework for Vision-Language Instruction Tuning models | 11 |
 ymcui/macbert | Improves pre-trained Chinese language models by incorporating a correction task to alleviate inconsistency issues with downstream tasks | 645 |
 yiyangzhou/lure | Analyzing and mitigating object hallucination in large vision-language models to improve their accuracy and reliability. | 134 |
 spandan-madan/pytorch_fine_tuning_tutorial | Provides guidance on fine-tuning pre-trained models for image classification tasks using PyTorch. | 279 |
 pku-alignment/safety-gymnasium | A unified benchmark for safe reinforcement learning algorithms and environments. | 394 |
 pku-yuangroup/languagebind | Extending pretraining models to handle multiple modalities by aligning language and video representations | 723 |
 jerry1993-tech/cornucopia-llama-fin-chinese | A Chinese finance-focused large language model fine-tuning framework | 589 |
 brightmart/xlnet_zh | Trains a large Chinese language model on massive data and provides a pre-trained model for downstream tasks | 230 |