diff options
Diffstat (limited to 'gguf-py/gguf/vocab.py')
| -rw-r--r-- | gguf-py/gguf/vocab.py | 33 |
1 files changed, 30 insertions, 3 deletions
diff --git a/gguf-py/gguf/vocab.py b/gguf-py/gguf/vocab.py index dc574991..cca09798 100644 --- a/gguf-py/gguf/vocab.py +++ b/gguf-py/gguf/vocab.py @@ -122,8 +122,30 @@ class SpecialVocab: tokenizer = json.load(f) if self.load_merges: merges = tokenizer.get('model', {}).get('merges') - if isinstance(merges, list) and merges and isinstance(merges[0], str): - self.merges = merges + if isinstance(merges, list) and merges: + if isinstance(merges[0], str): + self.merges = merges + elif isinstance(merges[0], list) and len(merges[0]) == 2 and isinstance(merges[0][0], str): + # New format since transformers 4.45 to support spaces in merges + # ref: https://github.com/ggml-org/llama.cpp/issues/9692 + # TODO: internally store as the new format instead of converting to old + if any(' ' in s for pair in merges for s in pair): + logger.warning(f'Spaces in merges detected, encoding as {chr(ord(" ") + 256)!r}') + self.merges = [ + ' '.join( + [ + # ensure the spaces are properly encoded + ''.join( + chr(ord(c) + 256) if c == ' ' else c + for c in part + ) + for part in pair + ] + ) + for pair in merges + ] + else: + raise ValueError("Unknown tokenizer merges format") added_tokens = tokenizer.get('added_tokens', {}) else: added_tokens = {} @@ -132,7 +154,12 @@ class SpecialVocab: return True with open(tokenizer_config_file, encoding = 'utf-8') as f: tokenizer_config = json.load(f) - chat_template = tokenizer_config.get('chat_template') + chat_template_alt = None + chat_template_file = path / 'chat_template.json' + if chat_template_file.is_file(): + with open(chat_template_file, encoding = 'utf-8') as f: + chat_template_alt = json.load(f).get('chat_template') + chat_template = tokenizer_config.get('chat_template', chat_template_alt) if chat_template is None or isinstance(chat_template, (str, list)): self.chat_template = chat_template else: |