AirLLM 70B inference with single 4GB GPU

pfmt-bench-fin-ja: Preferred Multi-turn Benchmark for Finance in Japanese

Train transformer language models with reinforcement learning.

This repository contains the relevant materials for the tutorial "Legal IR and NLP: the History, Challenges, and State-of-the-Art", held at ECIR 2023, 6th April, 2023.

Automated mass refactoring of source code.

Code examples and resources for DBRX, a large language model developed by Databricks

A Japanese Conversation Dataset for Real-world Reference Resolution (Ueda et al., LREC-COLING, 2024)

InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)

Plain text format for Japanese law

TCFD Criteria (joint work with Cierpa/JPX)

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Mamba SSM architecture

Japanese Language Model Financial Evaluation Harness

GitHub Pages

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

日本語LLMまとめ - Overview of Japanese LLMs

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

🤗 AutoTrain Advanced

AI-based Pull Request Summarizer and Reviewer with Chat Capabilities.

Inspect a command's effects before modifying your live system