language-model

◉ Universal Intelligence: AI made simple.

Our open source implementation of MiniLMv2 (https://aclanthology.org/2021.findings-acl.188)

[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text

🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드

Lightweight multilingual language models for consumer hardware

📚 Text Classification with LoRA (Low-Rank Adaptation) of Language Models - Efficiently fine-tune large language models for text classification tasks using the Stanford Sentiment Treebank (SST-2) dataset and the LoRA technique.

A developer-friendly template for building AI assistants that combines the best of LangServe, LangGraph, and assistant-ui into one seamless package.

Pre-training Language Models for Japanese

Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)

An interactive educational game built for the Google Gemma 3n Impact Challenge.

🧠 A production-grade, agentic RAG platform for portfolio intelligence, combining LangChain, Chroma/FAISS, Hugging Face embeddings, and Ollama with dynamic entity extraction, backend API tool-chaining, and a real-time interactive assistant across deploy-ready frontend, backend, and infrastructure stacks.

This repository contains a web application designed to execute relatively compact, locally-operated Large Language Models (LLMs).

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

🎯 Your free LLM evaluation toolkit helps you assess the accuracy of facts, how well it understands context, its tone, and more. This helps you see how good your LLM applications are.

spaCy-wrap is a wrapper library for spaCy for including fine-tuned transformers from Huggingface in your spaCy pipeline allowing you to include existing fine-tuned models within your SpaCy workflow.

Go implementation of today's most used tokenizers

Language Models as Hierarchy Encoders

RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!

LLM Agent paired with Image Captioning and Yolov8 models plays God of War

Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.