-
NS Solutions Corporation
- Yokohama, Japan
- http://sonoisa.github.io/
Stars
A Collection of BM25 Algorithms in Python
Japanese morphological analysis engine written in pure Python
A code-first agent framework for seamlessly planning and executing data analytics tasks.
JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
DSPy: The framework for programming—not prompting—language models
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
An LLM Based Diagnosis System (https://arxiv.org/pdf/2312.01454.pdf)
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
A guidance language for controlling large language models.
🦜🔗 Build context-aware reasoning applications
Integrate cutting-edge LLM technology quickly and easily into your apps
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
MCreator is an open-source software used to make Minecraft Java Edition mods, Minecraft Bedrock Edition Add-Ons, resource packs, and data packs using an intuitive easy-to-learn interface or with an…
Learning for effective and efficient bilevel planning
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
Building Open-Ended Embodied Agents with Internet-Scale Knowledge
MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
Create Minecraft bots with a powerful, stable, and high level JavaScript API.
数量表現や時間表現の抽出・正規化を行うNormalizeNumexpのPython実装
Tutorial to pretrain & fine-tune a 🤗 Flax T5 model on a TPUv3-8 with GCP
CLASP - Contrastive Language-Aminoacid Sequence Pretraining
Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.