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

convert : for Mamba, fallback to internal NeoX tokenizer

Browse source 
The resulting models are exactly the same
as if the tokenizer.json and tokenizer_config.json of GPT-NeoX were there.
This commit is contained in:
Francis Couture-Harpin 2024-03-02 23:39:19 -05:00
parent d52dd501f0
commit b83fbc9287
1 changed files with 27 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

29
convert-hf-to-gguf.py
View file

@ -1852,8 +1852,33 @@ class MambaModel(Model):
vocab_size = self.hparams["vocab_size"] vocab_size = self.hparams["vocab_size"]
# Round vocab size to next multiple of 8 # Round vocab size to next multiple of 8
pad_vocab = self.hparams.get("pad_vocab_size_multiple", 8) pad_vocab = self.hparams.get("pad_vocab_size_multiple", 8)
self.hparams["vocab_size"] = ((vocab_size + (pad_vocab - 1)) // pad_vocab) * pad_vocab # pad using ceiling division
return self._set_vocab_gpt2() # ref: https://stackoverflow.com/a/17511341/22827863
vocab_size = -(vocab_size // -pad_vocab) * pad_vocab
self.hparams["vocab_size"] = vocab_size
if (self.dir_model / "tokenizer.json").is_file():
self._set_vocab_gpt2()
else:
# Use the GPT-NeoX tokenizer when no tokenizer files are present
tokenizer_path = Path(sys.path[0]) / "models" / "ggml-vocab-gpt-neox.gguf"
print(f"Using tokenizer from '{os.path.relpath(tokenizer_path, os.getcwd())}'")
neox_reader = gguf.GGUFReader(tokenizer_path, "r")
field = neox_reader.get_field(gguf.Keys.Tokenizer.MODEL)
self.gguf_writer.add_tokenizer_model(bytes(field.parts[-1]))
field = neox_reader.get_field(gguf.Keys.Tokenizer.LIST)
self.gguf_writer.add_token_list([bytes(field.parts[i]) for i in field.data][:vocab_size])
field = neox_reader.get_field(gguf.Keys.Tokenizer.TOKEN_TYPE)
self.gguf_writer.add_token_types([field.parts[i].tolist()[0] for i in field.data][:vocab_size])
field = neox_reader.get_field(gguf.Keys.Tokenizer.MERGES)
self.gguf_writer.add_token_merges([bytes(field.parts[i]) for i in field.data])
field = neox_reader.get_field(gguf.Keys.Tokenizer.BOS_ID)
self.gguf_writer.add_bos_token_id(field.parts[-1].tolist()[0])
field = neox_reader.get_field(gguf.Keys.Tokenizer.EOS_ID)
self.gguf_writer.add_eos_token_id(field.parts[-1].tolist()[0])
field = neox_reader.get_field(gguf.Keys.Tokenizer.UNK_ID)
self.gguf_writer.add_unk_token_id(field.parts[-1].tolist()[0])
def set_gguf_parameters(self): def set_gguf_parameters(self):
d_model = self.hparams["d_model"] d_model = self.hparams["d_model"]