gpt2 = GPT2LMHeadModel.from_pretrained(âgpt2â, cache_dir=â./cacheâ, local_files_only=True)
gpt2.trainable = False
gpt2.config.pad_token_id=50256
gen_nlp = pipeline(âtext-generationâ, model=gpt2, tokenizer=tokenizer_gpt2, device=args.gpu, return_full_text=False)
contents = ds.df_train.sample(10)[âcontentâ].tolist()
results_trunk = gen_nlp(contents, max_length=64, do_sample=True, top_p=0.9, top_k=0,
repetition_penalty=1.0, num_return_sequences=4, clean_up_tokenization_spaces=True)
I use off-the-shelf GPT2 for open-ended generation. I find that there is a parameter
trainable
which needs to be set False or True before using.
Anyone know the nuance in this setting?
What is the best setting for this parameter?
Thanks.