# Chinese optimization

A quantized version based on the Baidu ERNIE-4.5-0.3B-PT model, optimized through the llama.cpp tool to reduce the model size and improve the running efficiency.

Skywork-SWE-32B is a large language model with 32B parameters. It is quantized by Llamacpp imatrix and can run efficiently in resource-constrained environments.

Qwen3 30B A3B is a large language model that has undergone 8-bit quantization using the GPTQ method, suitable for efficient inference scenarios.

Smoothie Qwen is a lightweight adjustment tool that can smooth the token probabilities in Qwen and similar models and enhance the multilingual balanced generation ability.

Qwen 3 is a language model based on the ExecuTorch runtime, offering both quantized and non - quantized versions of different scales.

This is a merged model based on Qwen2.5-32B, incorporating features from DeepSeek-R1-Distill-Qwen-32B, QwQ-32B, and Sky-T1-32B-Flash to enhance performance.

Qwen2.5-14B-YOYO-V5 is an enhanced version based on the Qwen2.5-14B foundation model, created by merging multiple pre-trained language models.

Qwen2.5-VL-7B-Instruct-GPTQ-Int4 is an unofficial GPTQ-Int4 quantized version based on the Qwen2.5-VL-7B-Instruct model, supporting multimodal tasks from image-text to text.

Qwen2-VL-7B-Instruct is a multimodal vision-language model that supports the joint understanding and generation of images and text.

Qwen2-VL-2B-Instruct is a vision-language model that provides a quantized version in GGUF format, suitable for the llama.cpp environment.

Moxin 7B is a powerful open-source large language model that offers various types such as base models and chat models, and has demonstrated good performance on multiple common datasets.

GLM-Edge-V-5B is a 5-billion-parameter multimodal model that supports image and text inputs, capable of performing image understanding and text generation tasks.

The Skywork Critic series of models are advanced judgment models that excel in paired preference evaluation. They can compare and evaluate a pair of input contents and provide detailed judgments.

The large language model of the Tongyi Qianwen Qwen2 series, which includes models with multiple parameter scales, ranging from 500 million to 72 billion parameters, and supports instruction tuning.

INT4 auto-quantized model based on Qwen2-7B, generated by Intel's auto-round tool, suitable for efficient inference tasks

Yi-1.5 is an upgraded version of the Yi model, excelling in programming, mathematics, reasoning, and instruction-following capabilities while maintaining excellent language understanding, commonsense reasoning, and reading comprehension.

This is an open-source model under the Apache-2.0 license. Specific information needs to be supplemented.

This is an open-source model based on the Apache-2.0 license. Specific functionalities should be referenced in the actual model documentation

ChatTruth-7B is a multilingual vision-language model optimized based on the Qwen-VL architecture, enhanced with large-resolution image processing capabilities and incorporating a restoration module to reduce computational overhead

Tess-M-v1.3 is a large language model trained on the Yi-34B-200K architecture, belonging to the general-purpose large language model series with ultra-long context processing capabilities.

GGUF-v3 version file of the Chinese LLaMA-2-7B model adapted to llama.cpp

A complete Chinese LLaMA-2-13B-16K model that supports a 16K context length and can be directly loaded for inference and full-parameter training

Alibaba PAI team's open-source Chinese latent diffusion model supporting Chinese text-to-image generation

ElasticBERT is an efficient multi-exit BERT model that supports dynamic adjustment of computational resources.

Chinese version of T5-large model specialized in natural language conversion tasks