请问我们的工作中，对于webshop的训练有提前进行SFT模型么？
xiaxiaxiatengxi opened this issue · 2 comments
xiaxiaxiatengxi commented
请问我们的工作中，对于webshop的训练有提前进行SFT模型么？
YifeiZhou02 commented
Yes, it is in the provided google drive link in the README.
DZ9 commented
Is gpt2_bc_workshop_history.pt the sft model for webshop? Does it means I need to load the model for training acther in rl step? How can I train a new sft model with different base LLM like Llama2? Thanks.