only small amount coming as output.

[EngOMAR2030]

trafficstars

I run the model and when running the model this message appears: Setting pad_token_id to eos_token_id:0 for open-end generation. Input length of input_ids is 21, but max_length is set to 20. This can lead to unexpected behavior. You should consider increasing max_new_tokens.

and the output is only small characters not so much of words like the demo of the model page in the huggingface website.

[ArmelRandy]

Can you share your code? As explained in the trace you should try to set the parameter max_new_tokens to be big enough for what you want to generate, for example model.generate(inputs, max_new_tokens=150). Another option is to use max_length. As a matter of fact, when you use generate without precising the value of the max_length argument, it is by default equal to 20. And that max_length parameter represents the length of the input prompt + max_new_tokens. So, if you want to generate something, you should choose max_length to be big enough considering the size of your prompt.

[EngOMAR2030]

Done that and worked.. thank you.