A simple, easy-to-use framework for HuggingFace and OpenAI text-generation models focused on explainability.

A set of bash scripts to automate deployment of GGML/GGUF models [default: RWKV] with the use of KoboldCpp on Android - Termux

Go bindings for llama.cpp and webui

Node-RED Flow (and web page example) for the Vicuna AI model

Testing of different IA engines like chat GPT based on the serge repo,

Boost productivity and power your workflow with Nano Bots for Visual Studio Code: small, AI-powered bots that can be easily shared as a single file, designed to support multiple providers such as Cohere Command, Google Gemini, Maritaca AI MariTalk, Mistral AI, Ollama, OpenAI ChatGPT, and others, with support for calling tools (functions).

Simplified local Windows OS setup of MiniGPT-4 running in an Anaconda environment; includes example local server and client.

This is small example for consumer api ollama server. This wants be one Gits for describe a client Ollama.

🦖 X—LLM: Simple & Cutting Edge LLM Finetuning

Free, Autonomous Self-Orchestrating Local Agent in Javascript.

Nano Bots for Obsidian: small, AI-powered bots that can be easily shared as a single file, designed to support multiple providers such as Cohere Command, Google Gemini, Maritaca AI, Mistral AI, Ollama, OpenAI ChatGPT, and others, + function calling.

A dummy test of Vicuna LLM in AWS instances.

A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.

This is a discord bot that uses ChatGPT or a local openai-compatible API as a backend.

Mental Model for better understanding LLM/Agent space

🌍 Simplify internationalization with language_wizard, a thread-safe key-value store for easy language switching and responsive event handling.

A chat interface using replicate and vicuna

This is a demo for using the Fastchat and OpenAI API for LLM summarization

Repository for personal experiments

Alpaca, Bloom, DeciLM, Falcon, Vicuna, Llama2, Zephyr, Mistral(MoE), RAG, Reranking, Langchain, Langsmith..