Stars
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
Implementation of Tree of Thoughts with LLM using LangChain for creative writing.
Industry leading face manipulation platform
Movie Gen Bench - two media generation evaluation benchmarks released with Meta Movie Gen
An Open-Sourced LLM-empowered Foundation TTS System
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
A simple yet powerful Python library for using LLMs
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Supercharge Your LLM Application Evaluations 🚀
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Skip the HTML, Bypass takes markdown and renders it directly on Android and iOS.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
An open-source RAG-based tool for chatting with your documents.
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
🤗更优雅的微信公众号订阅方式，支持私有化部署、微信公众号RSS生成（基于微信读书）v2.x
Port of Google's language-detection library to Python.
the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
Understand Human Behavior to Align True Needs
Copy the MLP of llama3 8 times as 8 experts , created a router with random initialization,add load balancing loss to construct an 8x8b MoE model based on llama3.
RoleInteract: Evaluating the Social Interaction of Role-Playing Agents
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs