Stars
Create web-based user interfaces with Python. The nice way.
Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️
📝 python package to calculate readability statistics of a text object - paragraphs, sentences, articles.
A Python library for calculating a large variety of metrics from text
A unified evaluation framework for large language models
[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
A guidance language for controlling large language models.
Accessible large language models via k-bit quantization for PyTorch.
Train transformer language models with reinforcement learning.
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
AirLLM 70B inference with single 4GB GPU
Automatically split your PyTorch models on multiple GPUs for training & inference
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
Source code of paper 'LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval' (WWW 2023)
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
The leading open-source AI copilot for JetBrains. Connect to any model in any environment, and customize your coding experience in any way you like.
A graph neural network tailored to directed acyclic graphs that outperforms conventional GNNs by leveraging the partial order as strong inductive bias besides other suitable architectural features.
TorchKGE: Knowledge Graph embedding in Python and PyTorch.
Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service
🔮 ChatGPT Desktop Application (Mac, Windows and Linux)
Algorithms for abstention, calibration and domain adaptation to label shift.
A high-throughput and memory-efficient inference and serving engine for LLMs
Python package for tackling multi-class imbalance problems. https://www.cs.put.poznan.pl/mlango/publications/multiimbalance/
[WWW 2022] Zero-Shot Stance Detection via Contrastive Learning
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.