search

the-crypt-keeper / can-ai-code

Self-evaluating interview for AI coders
https://huggingface.co/spaces/mike-ravkine/can-ai-code-results
MIT License
513 stars 29 forks source link

Evaluate Qwen-1.5-Chat Family #160

Closed the-crypt-keeper closed 6 months ago

the-crypt-keeper commented 7 months ago

https://huggingface.co/collections/Qwen/qwen15-65c0a2f577b1ecb76d786524

the-crypt-keeper commented 7 months ago

Finetune family: https://huggingface.co/collections/vilm/quyen-65bc71a29fa020161bc87859

the-crypt-keeper commented 6 months ago

ran the 4b - 72b models, all pass junior and all do poorly at senior with the 72b getting ~40% not going to bother with finetunes for now.