CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update convert-llama-h5-to-gguf.py

Browse Source
This commit is contained in:
klosax
2023-07-31 23:04:03 +02:00
committed by GitHub
parent f3de876a12
commit da4900e835
1 changed files with 0 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
convert-llama-h5-to-gguf.py
View File

@@ -104,11 +104,6 @@ if Path(dir_model + "/tokenizer.model").is_file():
print("Adding sentencepiece tokenizer vocab.") print("Adding sentencepiece tokenizer vocab.")
tokenizer = SentencePieceProcessor(dir_model + "/tokenizer.model") tokenizer = SentencePieceProcessor(dir_model + "/tokenizer.model")
# output vocab_size followed by all piece/score pairs
outbytes: bytes
outbytes = b""
outbytes += struct.pack("I", tokenizer.vocab_size())
for i in range(tokenizer.vocab_size()): for i in range(tokenizer.vocab_size()):
text: bytes text: bytes
if tokenizer.is_unknown(i): if tokenizer.is_unknown(i):