Hugging Face Python Packages

pydata-wrangler

Wrangle messy numerical, image, and text data into consistent well-organized formats

canifinetune

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

developergpt

DeveloperGPT is a LLM-powered command line tool that enables natural language to terminal commands and in-terminal chat.

fastrtc-whisper-cpp

A PyPI package that wraps Whisper.cpp for speech-to-text (STT) transcription, compatible with FastRTC

one-line-llm-tuner

This repository is the source code for fine tuning any LLM in just one line 🔥

dom-tokenizers

DOM-aware tokenization for Hugging Face language models

llm-app

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

deepspotm

Multimodal foundation model predicting transcriptome-wide virtual spatial transcriptomics from histology.

hf-cache-sync

Shared Hugging Face cache for teams. Sync local HF cache to Backblaze B2 or S3, eliminate repeated downloads, and enable fast, consistent model access across machines and CI.

rowgen

AI-powered SQL data generator using HuggingFace. Fill your database tables with realistic and context-aware data using AI.

project-fleming

Fleming repo to run semantic search models on databricks on CPU.