phonemetransformers/GPT2-85M-BPE-TXT
1570
GPT2 trained on the BabyLM 2024 training set using a BPE tokenizer.
Model trained for From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes.
GPT2 trained on the BabyLM 2024 training set using a BPE tokenizer.
Model trained for From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes.