# 8k Long Context

ReaRAG-9B is an enhanced model trained on glm-4-9b, capable of generating knowledge-guided reasoning chains and supporting iterative retrieval-augmented generation.

As of April 8, 2024, Yamshadow Experiment 28-7B is the top-performing 7B parameter model on the Open LLM Leaderboard. Use with caution, as this may indicate overfitting to benchmarks.

Kunoichi-7B is a 7B-parameter large language model that excels in both general-purpose tasks and role-playing capabilities, demonstrating outstanding performance across multiple benchmarks.

LeoLM is the first open-source commercial foundational language model for German based on the Mistral architecture, supporting 8k context length and specializing in German text generation tasks.

The first publicly available commercial German foundation language model based on Mistral 7b, extending Llama-2's German capabilities through large-scale German corpus continual pre-training.