# Model Fusion

DeepSeek-R1T-Chimera is an open-source weights model that combines the intelligence of DeepSeek-R1 with the token efficiency of DeepSeek-V3.

An 8B-parameter language model fused using the mergekit tool, generated via Passthrough fusion method

This is a pre-trained language model fused using the SLERP method, combining the strengths of both the pre-cursa-o1-v1.2 and post-cursa-o1 models.

BioMistral-MedMNX is a specialized language model in the biomedical field created by fusing multiple pre-trained models. It uses the DARE and TIES fusion methods to optimize performance.

BioMistral-7B-slerp is a medical domain language model merged using the SLERP method from BioMistral-7B and Mistral-7B-Instruct-v0.1, specializing in biomedical text processing

Sirius-10B is a large language model formed by the fusion of the TurdusBeagle-7B and Severus-7B models

blockchainlabs_7B_merged_test2_4 is a 7B-parameter large language model created by merging mlabonne/NeuralBeagle14-7B and udkai/Turdus using the mergekit tool.