root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-29 04:44:34 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
klosax 2023-08-20 16:54:42 +02:00 committed by GitHub
parent 28b8c265eb
commit 76b46627e2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 23 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
convert-llama-hf-to-gguf.py
View File

@ -173,18 +173,20 @@ if Path(dir_model + "/tokenizer.model").is_file():
gguf_writer.add_token_scores(scores) gguf_writer.add_token_scores(scores)
gguf_writer.add_token_types(toktypes) gguf_writer.add_token_types(toktypes)
print("gguf: get special token ids")
if Path(dir_model + "/tokenizer.json").is_file(): if Path(dir_model + "/tokenizer.json").is_file():
# Look for special tokens in tokenizer.json if it exists
with open(dir_model + "/tokenizer.json", "r", encoding="utf-8") as f: with open(dir_model + "/tokenizer.json", "r", encoding="utf-8") as f:
tokenizer = json.load(f) tokenizer = json.load(f)
if "added_tokens" in tokenizer and Path(dir_model + "/tokenizer_config.json").is_file(): if "added_tokens" in tokenizer and Path(dir_model + "/tokenizer_config.json").is_file():
print("gguf: get special token ids")
with open(dir_model + "/tokenizer_config.json", "r", encoding="utf-8") as f: with open(dir_model + "/tokenizer_config.json", "r", encoding="utf-8") as f:
tokenizer_config = json.load(f) tokenizer_config = json.load(f)
# find special token ids
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"]["content"]: if key["content"] == tokenizer_config["bos_token"]["content"]:
@ -209,6 +211,23 @@ if Path(dir_model + "/tokenizer.json").is_file():
for key in tokenizer["added_tokens"]: for key in tokenizer["added_tokens"]:
if 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"])
else:
# If no tokenizer.json: Look for special tokens in config.json
if "bos_token_id" in hparams and hparams["bos_token_id"] != None:
gguf_writer.add_bos_token_id(hparams["bos_token_id"])
if "eos_token_id" in hparams and hparams["eos_token_id"] != None:
gguf_writer.add_eos_token_id(hparams["eos_token_id"])
if "unk_token_id" in hparams and hparams["unk_token_id"] != None:
gguf_writer.add_unk_token_id(hparams["unk_token_id"])
if "sep_token_id" in hparams and hparams["sep_token_id"] != None:
gguf_writer.add_sep_token_id(hparams["sep_token_id"])
if "pad_token_id" in hparams and hparams["pad_token_id"] != None:
gguf_writer.add_pad_token_id(hparams["pad_token_id"])
# TENSORS # TENSORS