Hi Guys! Thanks in advance for any help.
I am currently fine tuning the llama2-7b base model, all went well and the model is working as excepted.
When I go to push this model to the model hub I am getting this error
ValueError: The generation config instance is invalid – .validate() throws warnings and/or exceptions. Fix these issues to save the configuration.
Thrown during validation:
[UserWarning(‘do_sample is set to False. However, temperature is set to 0.9 – this flag is only used in sample-based generation modes. You should set do_sample=True or unset temperature.’), UserWarning(‘do_sample is set to False. However, top_p is set to 0.6 – this flag is only used in sample-based generation modes. You should set do_sample=True or unset top_p.’)]
I got other warnings about do_sample so i actually decided to retrain the entire model with that config to see if it would help, that didnt work.
The files that saved are:
“adapter_config.json”
“adapter_model.safetensors”
“config.json”
I’m a bit confused about how to call these? Is my model saved?
Basically there are two questions
- Is there any workaround for pushing models to the model hub
- If not can I upload and call my model using the files I’ve listed above locally?
Hope you are having a great day!
Thanks!
