a toolkit on knowledge distillation for large language models
$ git clone https://github.com/modelscope/easydistill.git▲ +2 ★ this week
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
[ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
[EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models
Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.
ACM MM'23 (oral), SUR-adapter for pre-trained diffusion models can acquire the powerful semantic understanding and reasoning capabilities from large language models to build a high-quality textual semantic representation for text-to-image generation.
▲ +214 ★ this week
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Data from GitHub · snapshot Nov 13, 2026