Collection of fine-tuned models and expert adapters from the paper: "Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging"
Ryo Bertolissi
rbertolissi
AI & ML interests
None yet
Organizations
None yet
models
10
rbertolissi/Qwen2.5-1.5B-TTMM-GitHub-Python
Updated
rbertolissi/Qwen2.5-1.5B-TTMM-Wikipedia
Updated
rbertolissi/Llama-3.2-1B-TTMM-GitHub-Python
Updated
rbertolissi/Llama-3.2-1B-TTMM-Wikipedia
Updated
rbertolissi/Llama-3.2-1B-TTMM-MMLU
Updated
rbertolissi/Llama-3.2-1B-MMLU
Updated
rbertolissi/Qwen2.5-1.5B-GitHub-Python
Updated
rbertolissi/Llama-3.2-1B-GitHub-Python
Updated
rbertolissi/Qwen2.5-1.5B-Wikipedia
Updated
rbertolissi/Llama-3.2-1B-Wikipedia
Updated
datasets
0
None public yet