# Multi-domain Text Generation

A 12B-parameter multilingual large language model based on llama.cpp quantization, supporting role-play, story creation, and multi-domain professional tasks

Llama-3.1-Minitron-4B-Width-Base is a foundational text-to-text model obtained by pruning Llama-3.1-8B, suitable for various natural language generation tasks.

Minitron-8B-Base is a large language model obtained by pruning Nemotron-4 15B, employing distillation and continuous training methods, saving 40 times the training tokens and 1.8 times the computational cost compared to training from scratch.

A language model fine-tuned based on the Mixture of Experts (MoE) architecture, which fuses multiple models through the LazyMergekit framework and performs excellently in instruction tasks.