Fixes these issues:

`rope_scaling`'s beta_fast field must be a float, got 32

`rope_scaling`'s beta_slow field must be a float, got 1

ValueError: GenerationConfig is invalid: 
- `temperature`: `do_sample` is set to `False`. However, `temperature` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
- `top_p`: `do_sample` is set to `False`. However, `top_p` is set to `0.95` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.
If you're using a pretrained model, note that some of these attributes may be set through the model's `generation_config.json` file.

Also is the bos_token meant to be set? The pretrained model doesn't have one set, and when tokenizing these finetunes don't use one either?

natolambert changed pull request status to merged

Sign up or log in to comment