Efficient Triton Kernels for LLM Training
BSD-2-CLAUSE License
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet ...
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
A high-performance inference system for large language models, designed for production environments.
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qw...
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable fo...
Firefly: 大模型训练工具,支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixt...
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language M...
Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Fal...
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of...
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
AirLLM 70B inference with single 4GB GPU
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训...
KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델