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

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
1 changed files with 5 additions and 5 deletions
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: if "bos_token" in tokenizer_config and tokenizer_config["bos_token"] != None:
for key in tokenizer["added_tokens"]: 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"]) gguf_writer.add_bos_token_id(key["id"])
if "eos_token" in tokenizer_config and tokenizer_config["eos_token"] != None: if "eos_token" in tokenizer_config and tokenizer_config["eos_token"] != None:
for key in tokenizer["added_tokens"]: 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"]) gguf_writer.add_eos_token_id(key["id"])
if "unk_token" in tokenizer_config and tokenizer_config["unk_token"] != None: if "unk_token" in tokenizer_config and tokenizer_config["unk_token"] != None:
for key in tokenizer["added_tokens"]: 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"]) gguf_writer.add_unk_token_id(key["id"])
if "sep_token" in tokenizer_config and tokenizer_config["sep_token"] != None: if "sep_token" in tokenizer_config and tokenizer_config["sep_token"] != None:
for key in tokenizer["added_tokens"]: 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"]) gguf_writer.add_sep_token_id(key["id"])
if "pad_token" in tokenizer_config and tokenizer_config["pad_token"] != None: if "pad_token" in tokenizer_config and tokenizer_config["pad_token"] != None:
for key in tokenizer["added_tokens"]: 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"]) gguf_writer.add_pad_token_id(key["id"])