-
RFT Capital
- Los Angeles, California
Stars
Python implementation of OpenAI's realtime API
Build real-time multimodal AI applications 🤖🎙️📹
Redot Engine – Multi-platform 2D and 3D game engine
Open Sourced NoteBookLM
We write your reusable computer vision tools. 💜
Toolkit for attaching, training, saving and loading of new heads for transformer models
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
A Discord LLM chat bot that supports any OpenAI compatible API (OpenAI, xAI, Mistral, Groq, OpenRouter, ollama, LM Studio and more)
Open-Source Generative Agents is a community-driven fork of 'Generative Agents,' aimed at enabling compatibility with open-source Large Language Models; enhancing performance and adaptability; and …
Starter-kit to build constrained agents with Nextjs, FastAPI and Langchain
Openai GPT Vision - Dalle3 - CLI & Streamlit UI Image generator based on your input
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
Superfast AI decision making and intelligent processing of multi-modal data.
Fully customizable AI chatbot component for your website
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory
Voice activity detector (VAD) for the browser with a simple API
Official Demo Code for "Unlocking the Performance of Proximity Sensors by Utilizing Transient Histograms"
Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, langchain, D…
A language for constraint-guided and efficient LLM programming.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
8-bit CUDA functions for PyTorch, ported to HIP for use in AMD GPUs
A model compression and acceleration toolbox based on pytorch.