I am inheriting a mode pre-trained model: class GPT2FinetunedWithNgrams(GPT2LMHeadModel): @timer def __init__(self, config, model_tokenizer=None): super().__init__(config) self.tokenizer = GPT2Tokenizer.from_pretrained('gpt2', padding_side='right') self.tokenizer.pad…

Generate method during finetuning

thomwolf July 30, 2020, 10:02am 6

I see. Do you think you could to post a full and self-contained code example reproducing the bug?

Topic		Replies	Views
Loading finetuned model to generate text 🤗Transformers	12	3325	August 7, 2023
Encoder Decoder Model gives same generation results after finetuning 🤗Transformers	2	664	August 4, 2022
EncoderDecoderModel loaded from pre-trained checkpoints fails when calling generate 🤗Transformers	5	608	June 20, 2024
Issue with finetuning a seq-to-seq model 🤗Transformers	30	3962	August 11, 2022
Weird error when trying to generate response from fine-tuned model Beginners	1	206	April 2, 2024