The Brazilian scope routing model is a fine-tuned micro large language model based on Gemma 3 270M, specifically designed for the Brazilian food delivery service system. It can serve as an extremely fast and lightweight intent classifier (router). This model is trained using Unsloth and converted to the GGUF format.

Natural Language ProcessingSafetensorsOther

ZygAI is a fast local large language model designed specifically for Lithuanian and English tasks and is in the testing phase. As a lightweight bilingual assistant, it can run in real-time on local hardware, providing users with efficient and accurate bilingual services.

Natural Language ProcessingGgufMultiple Languages

Apriel-1.5-15b-Thinker is a multimodal reasoning model developed by the ServiceNow SLAM Lab, with a parameter scale of 15 billion. It has powerful text and image understanding and reasoning capabilities, adopting a chained reasoning mode of 'think-answer', aiming to achieve performance comparable to large models with a smaller model scale.

MultimodalTransformers

Apriel-1.5-15b-Thinker is a 15-billion parameter multimodal reasoning model developed by ServiceNow. It has the ability to reason with text and images, and its performance can rival models 10 times larger. It scored 52 points on the manual analysis index and performed excellently in enterprise domain benchmark tests.

MultimodalTransformers

Apriel-1.5-15b-Thinker is a multimodal reasoning model developed by ServiceNow, with 15 billion parameters. It performs excellently in text and image reasoning tasks and can compete with models 10 times larger than it.

MultimodalTransformers

This is the GGUF quantized version of the SynLogic-7B large language model developed by MiniMaxAI, with quantization services provided by TensorBlock. This model uses a 7B parameter scale, supports Chinese processing, and offers various quantization levels to meet different hardware requirements.

Natural Language ProcessingTransformersEnglish

This is the GGUF quantized format version of the unsloth/Jan-nano model, with quantization services provided by TensorBlock. This model is a lightweight large language model optimized to run in resource-constrained environments while maintaining good performance.

Natural Language ProcessingGguf

This is a 15B-parameter large language model built by the ServiceNow Language Model (SLAM) lab, quantized using the llama.cpp tool, suitable for local inference deployment.

Natural Language ProcessingGguf

Llama3.1-Typhoon2-8B is a large Thai language model (instructional type) based on the Transformer architecture, capable of handling various language tasks and providing users with efficient and accurate language interaction services.

Natural Language ProcessingSafetensors

This is a translation model with 418 million parameters, specifically designed to translate Yoruba, Igbo, and Hausa languages in Nigeria into English. The model is trained on a dataset containing 1.5 million pairs of sentences, aiming to provide high-quality translation services for these languages, enabling users to communicate with large language models more easily.

Natural Language ProcessingTransformersOther

Qwen2.5-72B-Instruct is a large language model with 72 billion parameters launched by Alibaba. It has been significantly improved on the basis of Qwen2, with rich knowledge reserves, excellent coding and mathematical abilities, supports long text processing and multilingual interaction, and can provide users with high-quality text generation and dialogue services.

Natural Language ProcessingSafetensorsEnglish

Xmodel-VLM is an efficient multimodal vision-language model designed for consumer-grade GPU servers. It solves the industry problem of high service costs for large-scale multimodal systems, significantly reducing deployment costs while maintaining high performance.

MultimodalTransformers

Vikhr-7B-instruct-GGUF is a large language model with 7 billion parameters based on the Mistral architecture, specifically optimized for text generation tasks in Russian and English. The model uses the GGUF quantization format, supporting efficient inference deployment and providing users with multilingual text interaction services.

Natural Language ProcessingGgufMultiple Languages

InternLM2 is an open-source large language model developed by the Shanghai Artificial Intelligence Laboratory. It has a 200K context window, excellent comprehensive performance, code interpreter and data analysis capabilities, and powerful tool usage capabilities, providing users with efficient and accurate text generation services.

Natural Language ProcessingTransformers

Stealth-v1.2 is an open-source large language model focused on text generation tasks. It performs excellently in multiple benchmark tests and can provide users with accurate and efficient text generation services. This model supports completely offline operation to ensure the confidentiality of conversation content.

Natural Language ProcessingTransformersEnglish

WiNGPT2 is a large-scale medical vertical domain model based on the GPT architecture, dedicated to integrating professional medical knowledge, healthcare information, and data to provide intelligent medical Q&A, diagnostic support, and medical knowledge services for the industry.

Natural Language ProcessingTransformersChinese

DISC-FinLLM is a large financial domain model developed based on Baichuan-13B-Chat, providing financial consulting, text analysis, calculation, and knowledge retrieval Q&A services.

Natural Language ProcessingTransformersChinese

WiNGPT2 is a large medical vertical domain model based on the GPT architecture, dedicated to integrating professional medical knowledge, healthcare information, and data to provide intelligent Q&A, diagnostic support, and medical knowledge services for the industry.

Natural Language ProcessingTransformersChinese

A Chinese legal domain large model developed by Fudan University's Data Intelligence and Social Computing Lab, providing intelligent legal services

Natural Language ProcessingTransformersChinese

DISC-MedLLM is a domain-specific large language model for medical dialogue scenarios developed by Fudan University's DISC Lab, built upon Baichuan-13b-base, providing high-quality health support services.

Natural Language ProcessingTransformersChinese