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

convert-hf : match model part name prefix and suffix

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-06-01 20:22:40 -04:00
parent e141ce624a
commit 3af9371811
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
convert-hf-to-gguf.py
View file

@ -72,10 +72,10 @@ class Model:
self.endianess = gguf.GGUFEndian.BIG if is_big_endian else gguf.GGUFEndian.LITTLE self.endianess = gguf.GGUFEndian.BIG if is_big_endian else gguf.GGUFEndian.LITTLE
self.use_temp_file = use_temp_file self.use_temp_file = use_temp_file
self.lazy = not eager self.lazy = not eager
self.part_names = Model.get_model_part_names(self.dir_model, ".safetensors") self.part_names = Model.get_model_part_names(self.dir_model, "model", ".safetensors")
self.is_safetensors = len(self.part_names) > 0 self.is_safetensors = len(self.part_names) > 0
if not self.is_safetensors: if not self.is_safetensors:
self.part_names = Model.get_model_part_names(self.dir_model, ".bin") self.part_names = Model.get_model_part_names(self.dir_model, "pytorch_model", ".bin")
self.hparams = Model.load_hparams(self.dir_model) self.hparams = Model.load_hparams(self.dir_model)
self.block_count = self.find_hparam(["n_layers", "num_hidden_layers", "n_layer"]) self.block_count = self.find_hparam(["n_layers", "num_hidden_layers", "n_layer"])
self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
@ -334,10 +334,10 @@ class Model:
self.gguf_writer.close() self.gguf_writer.close()
@staticmethod @staticmethod
def get_model_part_names(dir_model: Path, suffix: str) -> list[str]: def get_model_part_names(dir_model: Path, prefix: str, suffix: str) -> list[str]:
part_names: list[str] = [] part_names: list[str] = []
for filename in os.listdir(dir_model): for filename in os.listdir(dir_model):
if filename.endswith(suffix): if filename.startswith(prefix) and filename.endswith(suffix):
part_names.append(filename) part_names.append(filename)
part_names.sort() part_names.sort()