Sarvam-M is a multilingual, hybrid-reasoning, pure-text language model based on Mistral-Small, specifically optimized for Indian languages and English, featuring exceptional reasoning capabilities and cultural adaptability.

Natural Language ProcessingTransformersMultiple Languages

A powerful fine-tuned AI model based on HomerSlerp6-7B, integrating multiple Qwen2.5-7B series models to deliver high adaptability, deep knowledge, and engaging interaction experiences

Natural Language ProcessingTransformersEnglish

MN-Violet-Lotus-12B is a 12B-parameter large language model based on the merging of multiple high-quality models, specializing in roleplay and creative writing with outstanding emotional intelligence performance and broad character adaptability.

Natural Language ProcessingTransformersEnglish

A financial domain model developed based on Llama3-8B, enhanced with an instruction pretraining framework to improve domain adaptability, achieving or even surpassing the performance of Llama3-70B on financial tasks.

Natural Language ProcessingTransformersEnglish

This is a French automatic speech recognition model based on the FastConformer architecture, combining Transducer and CTC decoders for high accuracy and multi-domain adaptability.

Audio ProcessingPytorchFrench