# Instruction-tuned model

This is a large language model with 24B parameters based on the Mistral architecture, supporting text generation tasks and provided in GGUF format.

Cydonia-24B-v2.1 is a 24B parameter large language model, processed with llama.cpp's imatrix quantization, offering multiple quantized versions to suit different hardware requirements.

This is a 2.8 billion parameter MAMBA model fine-tuned on the OpenHermes dataset, featuring a novel state space architecture and excelling in text generation tasks.

PiVoT-0.1-early is a model fine-tuned based on Mistral 7B, focusing on text generation tasks and having different variant versions to meet different experimental needs.

OctoCoder is a 15.5 billion parameter instruction-tuned model, fine-tuned from StarCoder on the CommitPackFT and OASST datasets, supporting 80+ programming languages.

LaMini-T5-738M is an instruction-tuned model based on t5-large, fine-tuned on the LaMini-instruction dataset, with 738M parameters, and is one of the LaMini-LM series models.

LaMini-GPT-1.5B is a large language model fine-tuned based on the GPT-2-xl architecture, belonging to the LaMini-LM series, focusing on instruction-following tasks