Li Yu comments

Repositories
Issues
Comments

Results 5 comments of


                                            Li Yu

[BUG]Model size change

Hi [mkkk1112](https://github.com/mkkk1112), I got a similar error. I train with lora and merge the adapter layer with my base model (fp16). And it turn out the merged model is stored...

Inference

> Hi! Sorry for the unclearness, after Stage II is finished, the generated '.txt' file should be specified at the **'stage2_file'** variable in the config file, which is the last...

Hi! Did you solve this problem, my inference on hardi150 looks weird like this ![截屏2023-06-23 11 16 28](https://github.com/StanfordMIMI/DDM2/assets/51293901/017e4820-10f6-4bae-a0f9-927aa70a63e5) @tiangexiang @chenyzzz

GPU requirements results in error

Hi! I also got this error. Did you fix this? Thanks

demo of DPO with QLoRA (w Llama3 70B Instruct)

> Hi Andrew! Thank you for submitting this QLoRA&DPO implementation to LMFlow. I have reviewed and tested the changes and it looks good to me. > > 1. The curve...