liziniu

liziniu's Stars

• BlackHC/toma

  Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

  Language:Python43110

• OpenRLHF/OpenRLHF

  An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

  Language:Python3.4k317

• liziniu/ReMax

  Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

  Language:Python16113

• salesforce/LAVIS

  LAVIS - A One-stop Library for Language-Vision Intelligence

  Language:Jupyter Notebook10.1k980

• opendilab/awesome-RLHF

  A curated list of reinforcement learning with human feedback resources (continually updated)

  3.6k218

• baichuan-inc/Baichuan-7B

  A large-scale 7B pretraining language model developed by BaiChuan-Inc.

  Language:Python5.7k506

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python32.7k5k

• LinkSoul-AI/LLaSM

  第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

  Language:Python54155

• salesforce/BLIP

  PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

  Language:Jupyter Notebook4.9k655

• LlamaFamily/Llama-Chinese

  Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

  Language:Python14.3k1.3k

• Hiroki11x/LossLandscapeGeometry

  No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (ICML2024)

  Language:Shell7

• EmulationAI/awesome-large-audio-models

  Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

  62735

• google/python-fire

  Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

  Language:Python27.3k1.4k

• meta-llama/llama-recipes

  Scripts for fine-tuning Meta Llama 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 Llama for WhatsApp & Messenger.

  Language:Jupyter Notebook15.8k2.3k

• DLLXW/baby-llama2-chinese

  用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

  Language:Python2.6k317

• shibing624/MedicalGPT

  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练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

  Language:Python3.5k513

• artidoro/qlora

  QLoRA: Efficient Finetuning of Quantized LLMs

  Language:Jupyter Notebook10.1k826

• hpcaitech/ColossalAI

  Making large AI models cheaper, faster and more accessible

  Language:Python39k4.3k

• huggingface/peft

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

  Language:Python16.8k1.7k

• ymcui/Chinese-LLaMA-Alpaca-2

  中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

  Language:Python7.1k579

• longyuewangdcu/Chinese-Llama-2

  improve Llama-2's proficiency in comprehension, generation, and translation of Chinese.

  Language:Python53434

• huggingface/trl

  Train transformer language models with reinforcement learning.

  Language:Python10.4k1.3k

• facebookresearch/cc_net

  Tools to download and cleanup Common Crawl data

  Language:Python977143

• ekzhu/datasketch

  MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

  Language:Python2.6k296

• bigscience-workshop/data-preparation

  Code used for sourcing and cleaning the BigScience ROOTS corpus

  Language:Jupyter Notebook30542

• libprima/prima

  PRIMA is a package for solving general nonlinear optimization problems without using derivatives. It provides the reference implementation for Powell's derivative-free optimization methods, i.e., COBYLA, UOBYQA, NEWUOA, BOBYQA, and LINCOA. PRIMA means Reference Implementation for Powell's methods with Modernization and Amelioration, P for Powell.

  Language:Fortran32344

• p-lambda/dsir

  DSIR large-scale data selection framework for language model training

  Language:Python23919

• EleutherAI/the-pile

  Language:Python1.5k132

• PlexPt/awesome-chatgpt-prompts-zh

  ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

  53.4k13.5k

• facebookresearch/open_lth

  A repository in preparation for open-sourcing lottery ticket hypothesis code.

  Language:Python625112