root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 12:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

convert-llama-h5-to-gguf.py : special tokens

Browse Source
This commit is contained in:
klosax 2023-08-02 11:26:07 +02:00 committed by GitHub
parent e1e9b28547
commit c5ba5efda2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
convert-llama-h5-to-gguf.py
View File

@ -128,27 +128,27 @@ if Path(dir_model + "/tokenizer.json").is_file():
if "bos_token" in tokenizer_config and tokenizer_config["bos_token"] != None:
for key in tokenizer["added_tokens"]:
if key["content"] == tokenizer_config["bos_token"] or key["content"] == tokenizer_config["bos_token"]["content"]:
if key["content"] == tokenizer_config["bos_token"]["content"]:
gguf_writer.add_bos_token_id(key["id"])
if "eos_token" in tokenizer_config and tokenizer_config["eos_token"] != None:
for key in tokenizer["added_tokens"]:
if key["content"] == tokenizer_config["eos_token"] or key["content"] == tokenizer_config["eos_token"]["content"]:
if key["content"] == tokenizer_config["eos_token"]["content"]:
gguf_writer.add_eos_token_id(key["id"])
if "unk_token" in tokenizer_config and tokenizer_config["unk_token"] != None:
for key in tokenizer["added_tokens"]:
if key["content"] == tokenizer_config["unk_token"] or key["content"] == tokenizer_config["unk_token"]["content"]:
if key["content"] == tokenizer_config["unk_token"]["content"]:
gguf_writer.add_unk_token_id(key["id"])
if "sep_token" in tokenizer_config and tokenizer_config["sep_token"] != None:
for key in tokenizer["added_tokens"]:
if key["content"] == tokenizer_config["sep_token"] or key["content"] == tokenizer_config["sep_token"]["content"]:
if key["content"] == tokenizer_config["sep_token"]["content"]:
gguf_writer.add_sep_token_id(key["id"])
if "pad_token" in tokenizer_config and tokenizer_config["pad_token"] != None:
for key in tokenizer["added_tokens"]:
if key["content"] == tokenizer_config["pad_token"] or key["content"] == tokenizer_config["pad_token"]["content"]:
if key["content"] == tokenizer_config["pad_token"]["content"]:
gguf_writer.add_pad_token_id(key["id"])