Dia2 is a streaming dialogue text-to-speech (TTS) model developed by Nari Labs. It supports real-time speech generation and can start generating audio without the full text. It can be adjusted according to the dialogue context to achieve a natural and smooth dialogue experience.

Audio ProcessingSafetensorsEnglish

Dia2 is a streamed dialogue text-to-speech (TTS) model developed by Nari Labs. It supports real-time speech generation and can start generating audio without the need for the complete text. It is specifically designed for natural dialogue scenarios.

Audio ProcessingSafetensorsEnglish

zen-agent-4b is an intelligent agent for tool invocation with 4 billion parameters, supporting the Model Context Protocol (MCP), which provides strong assistance for text generation tasks. This model is developed by Zen Research DAO, affiliated with the non - profit organization Zoo Labs Inc.

Natural Language ProcessingTransformersEnglish

Tri-1.8B is a lightweight multilingual translation model launched by Trillion Labs. It has 1.8 billion parameters and supports bidirectional translation between English, Korean, Japanese, and Chinese. It features efficient deployment and excellent translation quality.

Natural Language ProcessingTransformersMultiple Languages

Cohere Labs Command A Vision is an enterprise-level vision-language model with 112 billion parameters, optimized for image understanding tasks. It has low computational requirements while maintaining high performance. The model supports multilingual input and output and can handle multimodal input of images and text.

MultimodalTransformersMultiple Languages

This is a quantized version of the Jamba-Mini-1.7 model from AI21 Labs, optimized using the imatrix technology of llama.cpp. It provides multiple quantization options for different hardware configurations and supports efficient reasoning.

Natural Language ProcessingGguf

Second-generation reasoning model developed by SmilyAI Labs, featuring a sarcastic antagonist-style AI persona with structured reasoning output

Natural Language ProcessingTransformersEnglish

A 7B-parameter open-source chart understanding vision-language model developed by Bespoke Labs, outperforming closed-source models like Gemini-1.5-Pro in chart QA tasks

MultimodalSafetensorsEnglish

Aya Expanse 8B is a highly advanced open-weight research model with multilingual capabilities, combining high-performance pre-trained models with a year of focused research by Cohere Labs.

Natural Language ProcessingTransformersMultiple Languages

Dia is a 1.6 billion parameter text-to-speech model developed by Nari Labs, capable of generating highly realistic dialogues directly from text, supporting emotional and intonation adjustments as well as non-verbal expression generation.

Dia is a 1.6 billion parameter text-to-speech model developed by Nari Labs, capable of generating highly realistic conversations directly from text, supporting emotional and tonal control, and producing non-verbal communication content.

Audio ProcessingSafetensorsEnglish

A text-to-speech model fine-tuned from Canopy Labs' pre-trained model, supporting English, using GGUF Q2_K quantization format for efficient inference

Audio ProcessingGgufMultiple Languages

A fine-tuned text-to-speech model based on Canopy Labs' pre-trained model, quantized for efficient inference

Audio ProcessingGgufMultiple Languages

A text-to-speech (TTS) model fine-tuned from Canopy Labs' pre-trained model, quantized in GGUF FP16 format for efficient inference

Audio ProcessingGgufMultiple Languages

An 8-bit quantized text-to-speech model fine-tuned from Canopy Labs' pre-trained model, supporting 24kHz English audio generation

Audio ProcessingGgufMultiple Languages

Cohere Labs Command A is a research version of a 111-billion parameter model with open weights, optimized for the demanding enterprise needs that require fast, secure, and high-quality AI.

Natural Language ProcessingTransformersMultiple Languages

BERTA is obtained by distilling the embedding vectors of the FRIDA model into LaBSE-ru-turbo, which is used to calculate the embedding vectors of Russian and English sentences and supports multiple prefix tasks.

Natural Language ProcessingTransformersMultiple Languages

Aya Vision 32B is an open-weight 32B parameter multimodal model developed by Cohere Labs, supporting vision-language tasks in 23 languages.

MultimodalTransformersMultiple Languages

This is a model checkpoint provided for the Any-to-Any subnet collaboration between OMEGA Labs and Bittensor, aiming to achieve general artificial intelligence tasks.

An any - to - any conversion model jointly developed by OMEGA Labs and Bittensor, focusing on the field of artificial general intelligence.