Get up and running with Llama 2 and other large language models
New set of lightweight state-of-the-art, open foundation models
Advanced language and coding AI model
Port of Facebook's LLaMA model in C/C++
Powerful AI language model (MoE) optimized for efficiency/performance
Python bindings for llama.cpp
Qwen3 is the large language model series developed by Qwen team
Run Local LLMs on Any Device. Open-source
Open-source, high-performance AI model with advanced reasoning
Open source LLM engineering platform: LLM Observability, metrics, etc.
The official repo of Qwen chat & pretrained large language model
A high-throughput and memory-efficient inference and serving engine
An LLM-powered knowledge curation system that researches topics
Dramatron uses large language models to generate coherent scripts
LLM Frontend for Power Users
Code for the paper "Evaluating Large Language Models Trained on Code"
ChatGLM-6B: An Open Bilingual Dialogue Language Model
Qwen2.5-VL is the multimodal large language model series
Ongoing research training transformer models at scale
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
Tools like web browser, computer access and code runner for LLMs
CogView4, CogView3-Plus and CogView3(ECCV 2024)
⚡ Building applications with LLMs through composability ⚡
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)