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

revert demo

Browse Source
This commit is contained in:
gauthiier 2022-02-10 14:38:39 +01:00
parent 2ea11e0dbd
commit 33d0fda2a2
1 changed files with 17 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
tokenise+train.py
View File

@ -28,19 +28,24 @@ def train(filepath: str, ouputdir: Path, blocksize: int, vocabsize: int, num_ste
else:
return "No valid tokenizer in " + str(ouputdir)
config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize, dropout=0.0, n_embd=256, n_layer=8, n_head=8)
# config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize, dropout=0.0, n_embd=256, n_layer=8, n_head=8)
# 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
# )
config = GPT2Config(
vocab_size=vocabsize,
max_lenght=blocksize,
n_positions=blocksize,
n_ctx=blocksize,
n_embd=256,
n_layer=8,
n_head=8,
dropout=0.0,
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)