Let us control diffusion models!

InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

LLM 实战

Fast and memory-efficient exact attention

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

Inference code for LLaMA models

Code and documentation to train Stanford's Alpaca models, and generate the data.

RISC-V Zve32x Vector Coprocessor

ocr_torch是基于Torch1.8实现的DBNet(2.2M) + CRNN(3.8M)实现的轻量级文字检测识别项目(支持onnx推理).

Make huge neural nets fit in memory