CValues
by X-PLUG
面向中文大模型价值观的评估与对齐研究
AI summary
Model value alignment
Evaluates and aligns the values of Chinese large language models with safety and responsibility standards
- stars
- 481
- forks
- 20
- watching
- 1
Similar projects
Found by comparing what the projects do, not just their names.
Safety fine-tuner
Improves safety and helpfulness of large language models by fine-tuning them using safety-critical tasks
Behavior alignment tool
Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy.
Chinese understanding benchmark
Measures the understanding of massive multitask Chinese datasets using large language models
Model aligner
Aligns large multimodal models with human intentions and values using various algorithms and fine-tuning methods.
Model interpreter
Provides tools to understand and interpret the decisions made by XGBoost models in machine learning
Chinese language model
Trains a large Chinese language model on massive data and provides a pre-trained model for downstream tasks
Multimodal LLM test suite
A benchmark for evaluating large language models' ability to process multimodal input
ethicalml/xai1.1K
Bias analysis tool
An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance
Model alignment
This project demonstrates the effectiveness of reinforcement learning from human feedback (RLHF) in improving small language models like GPT-2.
Chart eval
An evaluation suite for assessing chart understanding in multimodal large language models.
Hallucination tester
Evaluates and mitigates hallucinations in multimodal large language models
Alignment Benchmark
Generates a benchmark dataset for evaluating protein alignment programs
aidc-ai/ovis575
Multimodal aligner
An MLLM architecture designed to align visual and textual embeddings through structural alignment
Model evaluator
Evaluates the capabilities of large multimodal models using a set of diverse tasks and metrics
Chinese Text Model
An implementation of a large language model for Chinese text processing, focusing on MoE (Multi-Headed Attention) architecture and incorporating a vast vocabulary.
