api-inference is not working
#6
by
baby1
- opened
This comment has been hidden
either that or I need to change LLaMa to llama
tokenizer_class in tokenizer_config.json needs to be changed to: LlamaTokenizer
The model_type 'llama' is not recognized. It could be a bleeding edge model, or incorrect
Is it normal for the model to sometimes just to parrot the prompt with no additional text? Or is there a trick to setting the temperature, num_beams, top_p, etc.? I find it's hit and miss.