# Complex problem solving

DeepSeek-qwen-Bllossom-32B is built upon the DeepSeek-R1-Distill-Qwen-32B model, aiming to enhance reasoning performance in Korean environments.

Marco-o1 is an open reasoning model focused on open-ended solutions, enhancing complex problem-solving capabilities through chain-of-thought fine-tuning, Monte Carlo tree search, and reflection mechanisms.

A large language model fine-tuned on diverse scientific datasets based on Meta-Llama-3-8B, specializing in STEM domain tasks

StrangeMerges_53-7B-model_stock is the result of merging multiple 7B-parameter models using LazyMergekit, possessing powerful text generation capabilities.

Minotaur 13B is an instruction fine-tuned model based on LlaMA-13B, using entirely open-source datasets for fine-tuning to ensure reproducibility.