ConvAI-9b is a conversational AI model with 9 billion parameters, built by merging Zephyr-7b-beta and Mistral-7B-v0.2, suitable for interactive scenarios such as chatbots and virtual assistants.

Natural Language ProcessingTransformersEnglish

Zephyr 7B Gemma is a language model fine-tuned based on google/gemma-7b, trained on publicly available synthetic datasets using Direct Preference Optimization (DPO), designed to serve as a helpful assistant.

Natural Language ProcessingTransformers

OmniLMM-12B is a multimodal large model built upon EVA02-5B and Zephyr-7B-β, connected via perceptual resampling layers, trained with a progressive curriculum learning strategy, featuring outstanding performance, trustworthy behavior, and real-time multimodal interaction capabilities.

MultimodalTransformers

RankZephyr is a language model trained based on Zephyr-7B-β, specializing in listwise reranking tasks and excelling across multiple datasets.

Natural Language ProcessingTransformersEnglish

A Russian programming-enhanced model based on Zephyr-7b-beta, focused on Python code generation tasks

Natural Language ProcessingTransformersMultiple Languages

Starstreak-7b-beta is a multilingual large language model fine-tuned using QLoRA technology based on the Zephyr-7b-beta base model. This model has been specifically optimized and trained for English, Indonesian, and traditional Indonesian languages, and can generate high-quality text content. The model name is inspired by the Starstreak missile, symbolizing its ability to respond quickly.

Natural Language ProcessingTransformersMultiple Languages

Dialogue model fine-tuned on the ultrachat_200k dataset based on Mistral-7B

Natural Language ProcessingTransformers

Zephyr 7B Beta is a 7B parameter model based on the Mistral architecture of Hugging Face H4. It is optimized through AWQ quantization and suitable for efficient inference tasks.

Natural Language ProcessingTransformersEnglish