Chengdong Liang's repositories
deepseek-moe.cpp
Deepseek-moe deployment based on llama.cpp
HF_tokenizer_cpp
hugging face tokenizer库 C++版本
3D-Speaker
A repository for single- and multi-modal speaker verification, speaker recognition, and speaker diarization.
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
c_tokenizer
C api for huggingface tokenizer
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
ChatPiXiu
ChatPiXiu-Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXiu-貔貅 means fortune.
EAGLE
[ICML'24] EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
export_llama_to_onnx
export llama to onnx
ggml
Tensor library for machine learning
JittorLLMs
计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点
llama.cpp
Port of Facebook's LLaMA model in C/C++
llama.onnx
llama/alpaca onnx models, quantization and testcase
llm-export
llm-export can export llm model to onnx.
llm-papers
List of Large Lanugage Model Papers
OpenTextClassification
OpenTextClassification is all you need for text classification! Open text classification for everyone, enjoy your NLP journey! 这可能是目前为止最全面的开源文本分类项目，支持中英双语、多种模型、多种任务。
rwkv.cpp
INT4 and FP16 inference on CPU for RWKV language model
StableLM
StableLM: Stability AI Language Models
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.