vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Tokenizer SPM fixes for phi-3 and llama-spm (#7375)

Browse source 
* Update brute force test: special tokens
* Fix added tokens
  - Try to read 'added_tokens.json'.
  - Try to read 'tokenizer_config.json'.
  - Try to read 'tokenizer.json'.
* Fix special tokens rtrim

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* server : fix test regexes
This commit is contained in:
jaime-m-p 2024-05-20 20:15:57 +02:00 • committed by GitHub
parent fabf30b4c4
commit 917dc8cfa6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 98 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

32
convert-hf-to-gguf.py
View file

@ -1740,6 +1740,38 @@ class Phi3MiniModel(Model):
scores[token_id] = -1000.0
toktypes[token_id] = SentencePieceTokenTypes.USER_DEFINED
tokenizer_config_file = self.dir_model / 'tokenizer_config.json'
if tokenizer_config_file.is_file():
with open(tokenizer_config_file, "r", encoding="utf-8") as f:
tokenizer_config_json = json.load(f)
added_tokens_decoder = tokenizer_config_json.get("added_tokens_decoder", {})
for token_id, foken_data in added_tokens_decoder.items():
token_id = int(token_id)
token = foken_data["content"].encode("utf-8")
if toktypes[token_id] != SentencePieceTokenTypes.UNKNOWN:
assert(tokens[token_id] == token)
tokens[token_id] = token
scores[token_id] = -1000.0
toktypes[token_id] = SentencePieceTokenTypes.USER_DEFINED
if foken_data.get("special"):
toktypes[token_id] = SentencePieceTokenTypes.CONTROL
tokenizer_file = self.dir_model / 'tokenizer.json'
if tokenizer_file.is_file():
with open(tokenizer_file, "r", encoding="utf-8") as f:
tokenizer_json = json.load(f)
added_tokens = tokenizer_json.get("added_tokens", [])
for foken_data in added_tokens:
token_id = int(foken_data["id"])
token = foken_data["content"].encode("utf-8")
if toktypes[token_id] != SentencePieceTokenTypes.UNKNOWN:
assert(tokens[token_id] == token)
tokens[token_id] = token
scores[token_id] = -1000.0
toktypes[token_id] = SentencePieceTokenTypes.USER_DEFINED
if foken_data.get("special"):
toktypes[token_id] = SentencePieceTokenTypes.CONTROL
self.gguf_writer.add_tokenizer_model("llama")
self.gguf_writer.add_tokenizer_pre("default")
self.gguf_writer.add_token_list(tokens)