LyricZhao

Chenggang Zhao's starred repositories

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

Language:PythonGPL-3.060601 254 1500

llama

Inference code for LLaMA models

Language:PythonNOASSERTION50895 499 872

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

Language:TypeScriptNOASSERTION34451 276 2291

jina

☁️ Build multimodal AI applications with cloud-native stack

Language:PythonApache-2.020414 208 1937

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

Language:PythonNOASSERTION15573 134 615

peft

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

Language:PythonApache-2.014705 108 935

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Language:PythonApache-2.011905 137 195

flash-attention

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause11634 104 833

ChatRWKV

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Language:PythonApache-2.09333 91 115

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Language:C++Apache-2.07221 84 1476

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

Language:PythonMIT5832 65 147

GPU-Puzzles

Solve puzzles. Learn CUDA.

Language:Jupyter NotebookMIT5268 28 27

RDM

Easily set Mac Retina display to higher unsupported resolutions

Language:Objective-C++4099 68 54

openmlsys-zh

《Machine Learning Systems: Design and Implementation》- Chinese Version

Language:TeX3765 47 202

alpa

Training and serving large-scale neural networks with auto parallelization.

Language:PythonApache-2.03004 45 295

pytorch-GAT

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!

Language:Jupyter NotebookMIT2350 46 13