# Instruction optimization

Phi-mini-MoE is a lightweight Mixture of Experts (MoE) model suitable for English business and research scenarios, excelling in resource-constrained environments and low-latency scenarios.

Qwen3-Embedding-4B is a text embedding model built on the Qwen3 series, designed specifically for text embedding and ranking tasks, and performs excellently in multilingual text processing and code retrieval.

Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a range of dense and Mixture of Experts (MoE) models. Based on large-scale training, Qwen3 has achieved breakthrough progress in reasoning capabilities, instruction following, agent functionalities, and multilingual support.

This is a 24B-parameter merged language model, utilizing the TIES method to fuse multiple 24B-scale pre-trained models, focusing on providing high-quality text generation and comprehension capabilities.

Qwen2.5-7B-YOYO-super is an optimized open-source large language model achieved by merging base models and fine-tuned models, focusing on enhancing instruction-following, mathematical, and coding capabilities.

The GGUF format file of the Qwen2.5-1.5B-Instruct model, suitable for text generation tasks.

Llama-3.1-Storm-8B is a model developed based on Llama-3.1-8B-Instruct, aiming to improve the dialogue and function call capabilities of models with 8 billion parameters.

Badger is a Llama3 8B instruction model generated through recursive maximum pairwise disjoint normalized denoising Fourier interpolation method, incorporating features from multiple high-quality models.

This is a collection of pre-trained language models merged using the mergekit tool, based on the Llama-3-8B architecture and multiple derivative models.

Noro-Hermes-3x7B is a Mixture of Experts (MoE) model built using the lazy merge toolkit, combining three 7B-parameter Mistral variant models with capabilities in intelligent assistance, creative role-playing, and general task processing.

13B-Thorns is an instruction-based integrated and merged model of LLaMAv2-13B, using the Alpaca format, combining the advantages of multiple models to provide powerful language processing capabilities.