Notes from an independent NVFP4 port of Step-5-Preview
#11 opened 8 days ago
by 
alexmv2025
Add Terminal-Bench evaluation results
#10 opened 9 days ago
by 
nielsr
Which harnesses were used for the benchmarks? | 这些基准测试使用了哪些 Agent Harness？
#9 opened 18 days ago
by 
pandemo
Llama.cpp Support
👍 2
#8 opened 21 days ago
by 
Mdubbya
deploy on RTX6000 pro
#7 opened 21 days ago
by 
meffdata
Restore Agent's Last Exam with correct ale-cli-pass-rate task
#6 opened 22 days ago
by 
SaylorTwift
Remove Agent's Last Exam entry
#5 opened 22 days ago
by SaylorTwift
Add evaluation results
#4 opened 22 days ago
by SaylorTwift
Tool call feedback
#3 opened 23 days ago
by 
el4
Adding missing `pipeline_tag` annotation to enable inference providers to register
#2 opened 23 days ago
by 
wxgeorge