# Large Language Models

LongLoRA is an efficient fine-tuning technique for large language models with long context processing capabilities, achieving this through shifted short attention mechanisms, supporting context lengths from 8k to 100k.

The MathCoder series of open-source large language models, specifically tailored for general mathematical problem solving, fine-tuned based on Llama-2 and Code Llama.

WizardCoder is a large language model for code enhanced by the Evol-Instruct method, specializing in code generation tasks.

WizardMath-7B-V1.1 is a large language model trained on Mistral-7B, specializing in mathematical reasoning. It employs the Reinforced Evolutionary Instruction (RLEIF) method to enhance performance, currently achieving SOTA among 7B-scale mathematical models.