# Long text generation

An anime character chatbot based on the Mistral model, modeled after Senko from "Helping the Kitsune Lady", providing emotional support and warm dialogue experiences.

This is the quantized version of OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT. With quantization technology, the model can run more efficiently under different hardware conditions.

This is a model that uses the GPTQ method to perform 4-bit quantization on GLM-4-32B-0414, suitable for consumer-grade hardware.

This is the floating-point 16-bit version of Gryphe's MythoMax-L2-13B model converted to GGUF, designed for full-quality local inference on high-video-memory GPUs.

A preview version of a large language model fine-tuned specifically for Japanese novel writing assistance

ThinkAgain1.5 is a powerful text generation model with natural and intelligent reasoning capabilities, supporting tool invocation and functioning in various language scenarios.

The RWKV-7 g1 model based on the Flash linear attention mechanism, supporting multilingual processing and having deep thinking ability

A multi-stage training model based on Qwen2.5-14B and Qwen2.5-14B-Instruct, focusing on text generation and instruction understanding tasks.

Magnolia-v3-Gemma2-8k-9B is a model created by merging pre-trained language models using mergekit, providing a new solution for text generation.

A Gemma2 model optimized for novel and story creation, fine-tuned by integrating multiple top-notch story creation models, with more rich, delicate, and in-depth content generation capabilities.

A 12B-parameter language model merged using the mergekit tool, combining the anti-GPT features of UnslopNemo-12B-v4 and the intelligent performance of MN-12B-Mag-Mell-R1, suitable for creative writing and role-playing scenarios

A 70B-parameter large language model trained based on Llama 3.3 Instruct, specializing in dialogue generation and creative content creation

Magnum V4 72B is a member of the model series built on Qwen, aiming to replicate the prose quality of the Claude 3 series models and suitable for local AI chat applications.

Tucano-2b4 is a large - scale language model that is natively pre - trained specifically for Portuguese. It is based on the Transformer architecture and trained on the GigaVerbo dataset with 200 billion tokens.

Mistral-NeMo-Minitron-8B-Instruct is a text generation model developed by NVIDIA, supporting various tasks such as role-playing, retrieval-augmented generation, and function calls, with the characteristics of high efficiency and accuracy.

Experimental vision model combining keyword tags with long text descriptions for image prompt generation

YiSM-34B-0rn is a large language model based on the fusion of Yi-1.5-34B and Yi-1.5-34B-Chat, designed to balance instruction-following capabilities with foundational model characteristics.

This is a fusion model based on Mistral-7B-Instruct, combining DarkSapling's role-playing/story generation capabilities with some features of Bagel, utilizing Imatrix Plus compression technology to enhance quality

A Korean language model continuously pre-trained on the Llama-3-8B framework, trained with over 60GB of deduplicated text data

Orcamaid v3 13B 32K is a large language model based on the Llama architecture, supporting a sequence length of 32K and suitable for text generation tasks.

Korean-enhanced version based on SOLAR-10.7B-v1.0, continuously pre-trained by expanding vocabulary and Korean corpus

CyberAgentLM2 is a decoder-only language model pre-trained on 1.3 trillion tokens of publicly available Japanese and English datasets.

Pygmalion 2 7B is a large language model based on the LLaMA architecture, specializing in role-playing and dialogue generation tasks.

Based on the 13B parameter version of the LLaMA v2 base model, it excels in chatting, role-playing, and story creation, and has excellent reasoning and logical abilities.

Nous-Hermes-13B is a state-of-the-art language model fine-tuned on over 300,000 instructions, with performance comparable to GPT-3.5-turbo

4-bit (int4) quantized version of Chronos-13B, focused on chat, role-playing, and story creation, supporting long text generation

A Ukrainian text generation language model based on the GPT-2 architecture, featuring 124 million parameters and supporting Ukrainian text generation.

PULI 3SX is a 6.85 billion parameter Hungarian GPT-NeoX model, trained based on EleutherAI's GPT-NeoX architecture, suitable for text generation tasks.

This is a GPT2 large model (762 million parameters) trained from scratch, focusing on Dutch language, with a perplexity of 15.1 on the clean Dutch mC4 dataset.

BelGPT-2 is a GPT-2 model pre-trained on a massive French corpus (approximately 60GB), specializing in French text generation tasks.

A large Slovak language generation model with 1.4 billion parameters, based on the GPT - J architecture

This is a text generation model specifically fine-tuned for generating Hebrew poetry, based on hebrew-gpt_neo-xl

Transformer-XL is a causal Transformer architecture that uses relative position encoding. It can capture longer context by reusing previously computed hidden states, making it suitable for text generation tasks.