Mewral's Stars
ggerganov/llama.cpp
LLM inference in C/C++
openai/openai-cookbook
Examples and guides for using the OpenAI API
labmlai/annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
xai-org/grok-1
Grok open release
mlabonne/llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
guidance-ai/guidance
A guidance language for controlling large language models.
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
outlines-dev/outlines
Structured Text Generation
abetlen/llama-cpp-python
Python bindings for llama.cpp
01-ai/Yi
A series of large language models trained from scratch by developers @01-ai
PKU-YuanGroup/ChatLaw
ChatLaw:A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
openai/grok
eth-sri/lmql
A language for constraint-guided and efficient LLM programming.
Jittor/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
Tencent/NeuralNLP-NeuralClassifier
An Open-source Neural Hierarchical Multi-label Text Classification Toolkit
hiyouga/FastEdit
🩹Editing large language models within 10 seconds⚡
lhelontra/tensorflow-on-arm
TensorFlow for Arm
Xwin-LM/Xwin-LM
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
beyondguo/LLM-Tuning
Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.
thu-coai/Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
alibaba/rtp-llm
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
likenneth/honest_llama
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
lucidrains/st-moe-pytorch
Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
lucidrains/soft-moe-pytorch
Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch
Outsider565/LoRA-GA
PKU-Alignment/beavertails
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
Jellyfish042/uncheatable_eval
Evaluating LLMs with Dynamic Data
sakharamg/KITLM
Dan-wanna-M/bnf_sampler