gauthiier/NATURESPEAK-ML-UTTER
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

GPT2Config

Browse Source
This commit is contained in:
gauthiier 2022-02-09 18:49:18 +01:00
parent 58dd03ba73
commit c13bfa037a
1 changed files with 13 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
tokenise+train.py
View File

@ -28,7 +28,19 @@ def train(ouputdir: Path, blocksize: int, vocabsize: int, num_steps: int, gpu: b
tok = str(files[1]) tok = str(files[1])
dat = str(files[0]) dat = str(files[0])
config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize) # config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize)
config = GPT2Config(
vocab_size=vocabsize,
n_positions=blocksize,
n_ctx=blocksize,
resid_pdrop=0.0,
embd_pdrop=0.0,
attn_pdrop=0.0,
summary_first_dropout=0.0,
bos_token_id=0,
eos_token_id=0
)
print(config) print(config)