diff options
author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-08-12 15:14:32 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-08-12 15:14:32 +0200 |
commit | 8f43e551038af2547b5c01d0e9edd641c0e4bd29 (patch) | |
tree | 07a4373620a9381d0b5c7189a475990a6feb48a5 /gguf-py/gguf/gguf_writer.py | |
parent | f5d1af61d79fb53ccfbac2e665e43208c07b083d (diff) |
Merge mainline - Aug 12 2024 (#17)
* Merge mainline
* Fix after merge
* Remove CI check
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'gguf-py/gguf/gguf_writer.py')
-rw-r--r-- | gguf-py/gguf/gguf_writer.py | 14 |
1 files changed, 13 insertions, 1 deletions
diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py index ba6f53cd..76385a82 100644 --- a/gguf-py/gguf/gguf_writer.py +++ b/gguf-py/gguf/gguf_writer.py @@ -312,6 +312,8 @@ class GGUFWriter: self.add_key_value(key, val, GGUFValueType.STRING) def add_array(self, key: str, val: Sequence[Any]) -> None: + if len(val) == 0: + return self.add_key_value(key, val, GGUFValueType.ARRAY) @staticmethod @@ -826,6 +828,9 @@ class GGUFWriter: def add_eot_token_id(self, id: int) -> None: self.add_uint32(Keys.Tokenizer.EOT_ID, id) + def add_eom_token_id(self, id: int) -> None: + self.add_uint32(Keys.Tokenizer.EOM_ID, id) + def _pack(self, fmt: str, value: Any, skip_pack_prefix: bool = False) -> bytes: pack_prefix = '' if not skip_pack_prefix: @@ -845,7 +850,14 @@ class GGUFWriter: encoded_val = val.encode("utf-8") if isinstance(val, str) else val kv_data += self._pack("Q", len(encoded_val)) kv_data += encoded_val - elif vtype == GGUFValueType.ARRAY and isinstance(val, Sequence) and val: + elif vtype == GGUFValueType.ARRAY: + + if not isinstance(val, Sequence): + raise ValueError("Invalid GGUF metadata array, expecting sequence") + + if len(val) == 0: + raise ValueError("Invalid GGUF metadata array. Empty array") + if isinstance(val, bytes): ltype = GGUFValueType.UINT8 else: |