# Long-context processing

GreenMind-Medium-14B-R1 is a medium-scale Vietnamese language model capable of effectively solving problems requiring intermediate reasoning, such as common sense, mathematics, natural sciences, and social sciences topics.

Kanana 1.5 is a new version of the Kanana model family, featuring significant improvements in coding, mathematics, and function calling capabilities, supporting 32K tokens length and extendable to 128K tokens.

EXAONE Deep is an efficient reasoning language model developed by LG AI Research with 2.4B parameters, excelling in reasoning tasks such as mathematics and programming.

An 11-billion parameter large language model trained with the innovative SuperBPE tokenizer, supporting superword unit recognition and subword tokenization capabilities.

A modern bidirectional encoder-only Transformer model for Russian, pre-trained on approximately 2 trillion Russian, English, and code tokens, with a context length of up to 8,192 tokens.

A Korean-English bilingual enhanced model based on Llama3, optimized for Korean language capabilities through vocabulary expansion and knowledge correlation

StripedHyena-Nous-7B is a hybrid-architecture chat model combining multi-head grouped query attention and gated convolutions, supporting long-context processing.

StripedHyena-Hessian-7B is a Transformer alternative developed by Together Research based on a hybrid signal processing model, designed for long-context scenarios, offering more efficient training and inference performance.

MistralLite is a fine-tuned language model based on Mistral-7B-v0.1, enhanced for handling long contexts (up to 32K tokens), suitable for long-context retrieval, topic summarization, QA, and similar scenarios.

Chinese-LLaMA-2-7B-16K is a Chinese large language model developed based on Meta's Llama-2, supporting 16K context length, suitable for inference and full-parameter training.

Llama 2 is a 7B-parameter dialogue-optimized large language model developed by Meta. This version extends function calling capabilities, supporting structured JSON format responses.