artin/llama2.c
1
0
Fork 0
mirror of https://github.com/trholding/llama2.c.git synced 2026-02-06 11:26:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix sample.py from tokenizer changes before

Browse Source
This commit is contained in:
Andrej Karpathy 2023-08-15 02:33:01 +00:00
parent a9a0628c92
commit fe2de68688
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
sample.py
View File

@ -51,11 +51,16 @@ if compile:
print("Compiling the model...")
model = torch.compile(model) # requires PyTorch 2.0 (optional)
# load the tokenizer, either provided, or attempt to find it
# load the tokenizer
vocab_source = checkpoint_dict.get("vocab_source", "llama2")
vocab_size = gptconf.vocab_size
if tokenizer:
# a specific tokenizer is provided, use it
tokenizer_model = tokenizer
else:
tokenizer_model = get_tokenizer_model_path(vocab_size=gptconf.vocab_size)
# let's try to find the tokenizer model automatically. bit gross here...
query_vocab_size = 0 if vocab_source == "llama2" else vocab_size
tokenizer_model = get_tokenizer_model_path(vocab_size=query_vocab_size)
enc = Tokenizer(tokenizer_model=tokenizer_model)
# encode the beginning of the prompt