ShenDezhou's starred repositories
llm-playground
Experiments with open source LLMs
character-bert-pretraining
Code for pre-training CharacterBERT models (as well as BERT models).
ColossalAI-Examples
Examples of training models with hybrid parallelism using ColossalAI
LLM-Workshop
LLM Workshop by Sourab Mangrulkar
accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
ColossalAI
Making large AI models cheaper, faster and more accessible
Llama2-chinese
Llama2 chinese finetuning
llama2-lora-fine-tuning
llama2 finetuning with deepspeed and lora
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
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.
vscode-extension-samples
Sample code illustrating the VS Code extension API.
zero_shot_cot
Prod Env
natural-instructions
Expanding natural instructions
bert_distill
BERT distillation(基于BERT的蒸馏实验 )
duckdb-pgq
DuckDB is an in-process SQL OLAP Database Management System
arrow-tools
A collection of handy CLI tools to convert CSV and JSON to Apache Arrow and Parquet