# Creative text generation

Three quantized versions (Q8_0) of the Qwen 4B model, supporting 64K, 128K, and 256K context lengths, optimized for long-text generation and deep reasoning tasks

A NEO Imatrix quantized version based on the Qwen3-8B model, supporting 32K long context and enhanced reasoning ability

This is a NEO Imatrix quantized version based on the Qwen3-4B model, using BF16 format MAX output tensors to enhance reasoning and output generation capabilities, supporting 32k context length.

An 8B parameter large language model based on NEO CLASS technology, with a 32k context window and enhanced instruction-following ability

This is a hybrid model created through SLERP (Spherical Linear Interpolation) fusion of two 10.7B parameter models, combining the strengths of Fimbulvetr and Kuro-Lotus, demonstrating excellent performance in text generation tasks.

This is a 160M-parameter Llama chat model, fine-tuned from JackFram/llama-160m, focusing on text generation tasks.

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.

A BART-large fine-tuned model for automatically generating character setting prompts for ChatGPT