Milyausha Shamsutdinova
MilyaShams
AI & ML interests
NLP, LLM alignment
Organizations
None yet
Collection of merged models of DeepSeek-R1-Distill-Qwen-1.5B fine-tuned for adapting to medical domain in MedAdapt-LLM project.
-
MilyaShams/DeepSeek-R1-Distill-Qwen-1.5B-medical-continual-pretrain-merged
Text Generation • 2B • Updated • 1 -
MilyaShams/DeepSeek-R1-Distill-Qwen-1.5B-medical-msft-merged
Text Generation • 2B • Updated • 3 -
MilyaShams/DeepSeek-R1-Distill-Qwen-1.5B-medical-sft-merged
Text Generation • 2B • Updated • 2
Collection of merged models of DeepSeek-R1-Distill-Qwen-1.5B fine-tuned for adapting to medical domain in MedAdapt-LLM project.
-
MilyaShams/DeepSeek-R1-Distill-Qwen-1.5B-medical-continual-pretrain-merged
Text Generation • 2B • Updated • 1 -
MilyaShams/DeepSeek-R1-Distill-Qwen-1.5B-medical-msft-merged
Text Generation • 2B • Updated • 3 -
MilyaShams/DeepSeek-R1-Distill-Qwen-1.5B-medical-sft-merged
Text Generation • 2B • Updated • 2
The collection of aligned models based on SmolLM2 created during smol-course.