align-anything
Model aligner
Aligns large multimodal models with human intentions and values using various algorithms and fine-tuning methods.
Align Anything: Training All-modality Model with Feedback
270 stars
9 watching
53 forks
Language: Python
last commit: 3 months ago chameleondpolarge-language-modelsmultimodalrlhfvision-language-model
Related projects:
| Repository | Description | Stars |
|---|---|---|
 pku-yuangroup/languagebind | Extending pretraining models to handle multiple modalities by aligning language and video representations | 751 |
 aidc-ai/ovis | An MLLM architecture designed to align visual and textual embeddings through structural alignment | 575 |
 ethanyanjiali/minchatgpt | This project demonstrates the effectiveness of reinforcement learning from human feedback (RLHF) in improving small language models like GPT-2. | 214 |
 lancopku/iais | This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs. | 30 |
 x-plug/cvalues | Evaluates and aligns the values of Chinese large language models with safety and responsibility standards | 481 |
 rlhf-v/rlhf-v | Aligns large language models' behavior through fine-grained correctional human feedback to improve trustworthiness and accuracy. | 245 |
| pku-yuangroup/video-bench | Evaluates and benchmarks large language models' video understanding capabilities | 121 |
 pkunlp-icler/pca-eval | An open-source benchmark and evaluation tool for assessing multimodal large language models' performance in embodied decision-making tasks | 99 |
 cmesher/inuktitutalignerdata | Scripts for aligning laboratory speech production data in Inuktitut | 3 |
| pku-yuangroup/moe-llava | A large vision-language model using a mixture-of-experts architecture to improve performance on multi-modal learning tasks | 2,023 |
 prosodylab/prosodylab-aligner | Tools for aligning laboratory speech production data to forced audio alignment using HTK and SoX. | 333 |
 mshukor/evalign-icl | Evaluating and improving large multimodal models through in-context learning | 21 |
 multimodal-art-projection/omnibench | Evaluates and benchmarks multimodal language models' ability to process visual, acoustic, and textual inputs simultaneously. | 15 |
 jcgood/rosetta-pangloss | A Python library that uses machine learning and natural language processing to improve translation accuracy by aligning source and target languages | 0 |
 opengvlab/multi-modality-arena | An evaluation platform for comparing multi-modality models on visual question-answering tasks | 478 |