GLM-4.6 is a new-generation text generation model launched by Zhipu AI. Compared with GLM-4.5, it has significant improvements in multiple aspects, including a longer context window, better coding performance, and stronger reasoning ability. This model performs excellently in multiple public benchmark tests and has a competitive advantage compared with leading models at home and abroad.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.6-FP8 is a new-generation text generation model launched by Zhipu AI. It has significant improvements in multiple key aspects compared to GLM-4.5. This model has a longer context window, excellent coding performance, advanced reasoning ability, and more powerful agent functions, enabling it to handle more complex tasks.

Natural Language ProcessingTransformersMultiple Languages

Devstral 1.1 is an intelligent large language model jointly developed by Mistral AI and All Hands AI, specifically designed for software engineering tasks. This model performs excellently in the SWE-bench benchmark test, ranking first among open-source models. It has 24 billion parameters and a long context window of 128k tokens.

Natural Language ProcessingSafetensorsMultiple Languages

AuriStream-1B is a biologically inspired GPT-style autoregressive Transformer model specifically designed to predict cochlear markers in long speech contexts. The model uses a long context window of approximately 20 seconds (4096 tokens) and was trained on the LibriLight dataset (approximately 60,000 hours) for about 500,000 steps. It can learn rich time-aligned representations and generate speech continuations.

Audio ProcessingTransformersEnglish

A merged model based on Llama 3 70B, optimized for story creation and role-playing, supporting long context windows

Natural Language ProcessingTransformers

A merged model based on Llama 3 70B architecture, optimized for story generation and role-play, supporting long context windows

Natural Language ProcessingTransformers

Dewey is a novel long-context embedding model based on the ModernBERT architecture, supporting a 128k context window and excelling in long-document retrieval tasks.

Natural Language ProcessingTransformersEnglish

TVC-7B is a 7 billion parameter model based on Qwen2-VL-7B-Instruct. It supports both Chinese and English, has an 8K token context window, and excels in long-chain reasoning and multimodal processing.

MultimodalTransformers

VideoChat-Flash is a multimodal model built upon UMT-L and Qwen2.5-7B-1M, supporting long video understanding with an extended context window of 1M.

MultimodalTransformersEnglish

A multimodal model built on UMT-L and Qwen2-7B, supporting long video understanding with only 16 tokens per frame and an extended context window of 128k.

MultimodalTransformersEnglish

LongCite-llama3.1-8b is a model trained based on Meta-Llama-3.1-8B, focusing on long context Q&A and generating fine-grained references, supporting a context window of up to 128K tokens.

Natural Language ProcessingTransformersMultiple Languages

Yarn Mistral 7B 128K is an advanced language model optimized for long-context processing, further pre-trained on long-context data using the YaRN extension method, supporting a 128k token context window.

Natural Language ProcessingTransformersEnglish