[doc] FAQ
Cannot download result on OpenXLab
This is https vs http problem. Just use https://g-app-center-120612-6433-jpdvmvp.openxlab.space instead of https://openxlab.org.cn/apps/detail/chenzihonga/GraphGen
Or you can:
STEP1. right-click download button and "copy link"
STEP2. open a new broswer tab, input the link
Why not CP (Continue Pretraining) / How about base model know nothing about the domain knowledge ?
When SFT data is sufficient, the model can also learn new knowledge. Completing "data cleaning-CP-SFT-DPO" from scratch costs hundreds of thousands of dollars. As an engineer rather than an academic researcher, GraphGen is the best solution we can give.
Why all of output loss are same value?
See #17 and try vllm serve with v0.6.6post1 version.
logprobs in v0.8.3 still fails https://github.com/vllm-project/vllm/issues/16838