Qwen/Qwen1.5-MoE-A2.7B
Text Generation • 14B • Updated • 204k • 228
Deployable Intelligence
Models and datasets for "Quantifying deployable intelligence in mixture-of-experts language models".
-
-
deepseek-ai/DeepSeek-V2-Lite
Text Generation • 16B • Updated • 498k • 183 -
mistralai/Mixtral-8x7B-v0.1
47B • Updated • 47.8k • 1.82k -
allenai/c4
Viewer • Updated • 10.4B • 1.61M • 624 -
Salesforce/wikitext
Viewer • Updated • 3.71M • 1.46M • 754 -
ptb-text-only/ptb_text_only
Updated • 23.7k • 20 -
cais/mmlu
Viewer • Updated • 231k • 468k • 809 -
openai/gsm8k
Benchmark • Updated • 17.6k • 950k • 1.47k -
EleutherAI/hendrycks_math
Viewer • Updated • 12.5k • 119k • 107 -
openai/openai_humaneval
Viewer • Updated • 164 • 234k • 397 -
google-research-datasets/mbpp
Viewer • Updated • 1.4k • 172k • 233 -
allenai/winogrande
Viewer • Updated • 81.4k • 233k • 85 -
Rowan/hellaswag
Viewer • Updated • 60k • 289k • 188
aps/super_glue
Viewer • Updated • 196k • 159k • 188Note Please use boolq and rte.
-
allenai/ai2_arc
Viewer • Updated • 7.79k • 439k • 378 -
allenai/openbookqa
Viewer • Updated • 11.9k • 160k • 135 -
ybisk/piqa
Updated • 64.2k • 106