# Multi-task reasoning

Mi:dm 2.0 is an AI model centered around South Korea, developed by KT using its proprietary technology. This model has deeply internalized the unique values, cognitive frameworks, and common-sense reasoning of South Korean society. It can not only process and generate Korean content but also reflect a profound understanding of South Korean social and cultural norms and values.

An 8B-parameter large language model fused via MergeKit from multiple high-quality models, optimized for reasoning, dialogue, and creative generation

Hunyuan-7B-Instruct is a bilingual (Chinese-English) large language model released by Tencent, featuring powerful text generation and comprehension capabilities, and is one of the strongest Chinese 7B Dense models currently available.

DeepSeek-R1 is the first-generation inference model, which performs excellently in mathematics, code, and reasoning tasks, and its performance is comparable to that of OpenAI-o1.

Gemma is a lightweight open-source large language model launched by Google, built with the same technology as Gemini, suitable for text generation tasks.

A large language model fine-tuned via DPO based on Meta-Llama-3-70B-Instruct, demonstrating excellent performance in multiple benchmark tests

Rhea-72b-v0.5 is a large language model fine-tuned based on Smaug-72B-v0.1, ranking first on the HuggingFace Open LLM Leaderboard.

Ghost 7B is a large language model focused on optimizing reasoning and multi-task knowledge, supporting English and Vietnamese, based on the Mistral 7B architecture.

orthogonal-2x7B-v2-base is a Mixture of Experts model based on Mistral-7B-Instruct-v0.2 and SanjiWatsuki/Kunoichi-DPO-v2-7B, specializing in text generation tasks.

OpenOrca-Platypus2-13B is a fusion model combining Platypus2-13B with OpenOrcaxOpenChat-Preview2-13B, integrating the advantages of STEM/logic datasets and GPT-4 refined datasets