Azure99

Azure99's starred repositories

dagster

An orchestration platform for the development, production, and observation of data assets.

Language:PythonApache-2.01051300

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

Language:C++Apache-2.0314600

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Language:PythonApache-2.0294900

text-generation-inference

Large Language Model Text Generation Inference

Language:PythonApache-2.0819700

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonMIT548600

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

1231400

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it.

Language:PythonMIT5100400

uniem

unified embedding model

Language:PythonApache-2.077000

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

Language:PythonAGPL-3.03759800

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Language:PythonMIT397100

Blink

Modern Desktop Jellyfin Client made with Tauri and React :atom_symbol: [WIP]

Language:TypeScriptGPL-3.059200

vllm

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

Language:PythonApache-2.02074400

Visual-Chinese-LLaMA-Alpaca

多模态中文LLaMA&Alpaca大语言模型（VisualCLA）

Language:PythonApache-2.038300

h2ogpt

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/

Language:PythonApache-2.01085100

buildkit

concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit

Language:GoApache-2.0776600

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.

Language:GoBSD-3-Clause995600