423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 15:52:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit from fork

Browse Source
This commit is contained in:
hoshi-hiyouga 2025-04-23 16:38:27 +08:00 committed by GitHub
parent c1a7f2ebb2
commit 091d2539e8
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/convert_ckpt/llamafy_baichuan2.py
View File

@ -32,7 +32,7 @@ def save_weight(input_dir: str, output_dir: str, shard_size: str, save_safetenso
baichuan2_state_dict: dict[str, torch.Tensor] = OrderedDict() baichuan2_state_dict: dict[str, torch.Tensor] = OrderedDict()
for filepath in tqdm(os.listdir(input_dir), desc="Load weights"): for filepath in tqdm(os.listdir(input_dir), desc="Load weights"):
if os.path.isfile(os.path.join(input_dir, filepath)) and filepath.endswith(".bin"): if os.path.isfile(os.path.join(input_dir, filepath)) and filepath.endswith(".bin"):
shard_weight = torch.load(os.path.join(input_dir, filepath), map_location="cpu") shard_weight = torch.load(os.path.join(input_dir, filepath), map_location="cpu", weights_only=True)
baichuan2_state_dict.update(shard_weight) baichuan2_state_dict.update(shard_weight)
llama_state_dict: dict[str, torch.Tensor] = OrderedDict() llama_state_dict: dict[str, torch.Tensor] = OrderedDict()