Stars
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
A generative speech model for daily dialogue.
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
SGLang is a fast serving framework for large language models and vision language models.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilizatio…
Multilingual Voice Understanding Model
web-based visualization libraries
An open-source LLM tool for extracting repeatable tasks from your conversations, and saving them into a customized skill library for retrieval.
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
ModelScope-Agent: An agent framework connecting models in ModelScope with the world
A blazing fast inference solution for text embeddings models
🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.
A batched offline inference oriented version of segment-anything
A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
A programming framework for agentic AI 🤖
The RedPajama-Data repository contains code for preparing large datasets for training large language models.