Super simple MLX (apple silicon) CLIP based photo similarity web app📸 Embed-Photos 🖼️ Welcome to Embed-Photos, a powerful photo similarity search engine built by @harperreed! 🎉 This project leverages the CLIP (Contrastive Language-Image Pre-training) model to find visually similar images based on textual descriptions. 🔍🖼️ 🌟 Features 🚀 Fast and efficient image search using the CLIP model 💻 Works on Apple Silicon (MLX) only 💾 Persistent storage of image embeddings using SQLite and Chroma 🌐 Web …
Form Extractor Prototype This tool extracts the structure from an image of a form. It uses the Claude 3 LLM model by Anthropic. A single extraction of an A4 form costs about 10p. It replicates the form structue in JSON, following the schema used by GOV.UK Forms. It then uses that to generate a multi-page web form in the GOV.UK style. Run locally You'll need an Anthropic API key. Add the key as a local environment variable called ANTHROPIC_API_KEY. Install the app locally with npm install. S…
Inference code for Llama modelsLlama 2 We are unlocking the power of large language models. Our latest version of Llama is now accessible to individuals, creators, researchers, and businesses of all sizes so that they can experiment, innovate, and scale their ideas responsibly. This release includes model weights and starting code for pre-trained and fine-tuned Llama language models — ranging from 7B to 70B parameters. This repository is intended as a minimal example to load Llama 2 models and …
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & MessengerLlama Recipes: Examples to get started using the Llama models from Meta The 'llama-recipes' repository is a companion to the Meta Llama 2 an…
A multiplayer chess platform similar to https://chess.com/Chess Building a platform where people can Sign up Create a new match/get connected to an existing match During the match, let users play moves Have a rating system that goes up and down similar to standard chess rating Tech stack Let's keep it simple React for Frontend Node.js for Backend Typescript as the language Saparate Websocket servers for handling real time games Redis for storing all moves of a game in a queue
The official Meta Llama 3 GitHub site 🤗 Models on Hugging Face | Blog | Website | Get Started Meta Llama 3 We are unlocking the power of large language models. Our latest version of Llama is now accessible to individuals, creators, researchers, and businesses of all sizes so that they can experiment, innovate, and scale their ideas responsibly. This release includes model weights and starting code for pre-trained and instruction tuned Llama 3 language models — including si…
LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo Key functionality Choose your model, choose or add your prompt, run the inference. Browse contribution graph. Select the token to build the graph from. Tune the contribution threshold. Select representation of any token after any block. For the representation, see it…
🔥 Turn entire websites into LLM-ready markdown🔥 Firecrawl Crawl and convert any website into LLM-ready markdown. Build by Mendable.ai This repository is currently in its early stages of development. We are in the process of merging custom modules into this mono repository. The primary objective is to enhance the accuracy of LLM responses by utilizing clean data. It is not ready for full self-host yet - we're working on it What is Firecrawl? Firecrawl is an API service that takes a URL, craw…
Inference code for CodeLlama modelsIntroducing Code Llama Code Llama is a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide multiple flavors to cover a wide range of applications: foundation models (Code Llama), Python specializations (Code Llama - Python), and instruction-following models (Code …