HelloSun
/

minicpm47woek_EPQ

Text Generation

Mixture of Experts

expert-offloading

Model card Files Files and versions

minicpm47woek_EPQ / bench

117 kB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

HelloSun's picture

EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M

12eb3a5 verified 7 days ago

results
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
expert_index.json

33.2 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
run_budget_curve.py

4.91 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
run_n9.py

6.11 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
run_negative.py

6.05 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
run_ramsweep.py

5.12 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
summarize.py

4.71 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago
upload.py

1.86 kB
EPM: expert paging CPU inference for MiniCPM-V-4.7-35B-A3B Q4_K_M 7 days ago