🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Large Language Model Text Generation Inference

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Repo for BenTsao [original name: HuaTuo (华驼)], Instruction-tuning Large Language Models with Chinese Medical Knowledge. 本草（原名：华驼）模型仓库，基于中文医学知识的大语言模型指令微调

雅意大模型：为客户打造安全可靠的专属大模型，基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM 系列模型，由中科闻歌算法团队研发。(Repo for YaYi Chinese LLMs based on LlaMA2 & BLOOM)

中文nlp解决方案(大模型、数据、模型、训练、推理)

Go package implementing Bloom filters, used by Milvus and Beego.

🩹Editing large language models within 10 seconds⚡

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

C++ implementation for BLOOM

Spicetify theme inspired by Microsoft's Fluent Design, Always up-to-date!, A Powerful Theme to Calm your Eyes While Listening to Your Favorite Beats

Fast Inference Solutions for BLOOM

Crosslingual Generalization through Multitask Finetuning

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

OpenGL C++ Graphics Engine

💬 Chatbot web app + HTTP and Websocket endpoints for LLM inference with the Petals client

Cuckoo Filter go implement, better than Bloom Filter, configurable and space optimized 布谷鸟过滤器的Go实现，优于布隆过滤器，可以定制化过滤器参数，并进行了空间优化

DirectX 11 Renderer written in C++11

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).