huggingface

High-performance .NET BPE tokenizer — up to 618 MiB/s, competitive with Rust. Zero-allocation counting, multilingual cache, o200k/cl100k/r50k/p50k encodings + HuggingFace tokenizer.json support.

ScrapeGPT is a RAG-based Telegram bot designed to scrape and analyze websites, then answer questions based on the scraped content. The bot utilizes Retrieval Augmented Generation and webscraping to return natural language answers to the user's queries.

Huggingface utilities for Ultralytics/YOLOv8

Conveniently download files, models, tokenizers from HuggingFace Hub

Learn n8n workflow automation with AI Agents 🤖 | Step-by-step guide to build no-code workflows, automate tasks, and create intelligent pipelines 🚀 | Integrate OpenAI, Hugging Face, LLMs, and external APIs 🌐 | Master chatbots, data automation, and smart workflows using n8n. 🧠

ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data Poisoning, PII, and Prompt Injections. Secure your AI Supply Chain.

An implementation of GRPO for Unsloth's VLMs training

Apply controlnet to video clips

SDK for using LLM

Chef Transformer 🍲 .

GitHub action that'll sync files from a GitHub Repo with the Hugging Face Hub 🤗

Self-contained UV scripts for data & ML tasks. Includes OCR, vision, audio & more. Run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.

Easy to use pretrained yolov5 models

Build your own Custom RAG Chatbot using Gradio, Langchain and Llama2

Completion After Prompt Probability. Make your LLM make a choice

A fine-tuned model based on Stable Diffusion to create images in the style of Midjourney

Repository for the companion Colab notebook of the Domain-Specific Small Language Models book.

This repo contains a list of channels and sources from where LLMs should be learned

Tensorflow, Pytorch, Huggingface Transformer, Fastai, etc. tutorial Colab Notebooks.