kanshan/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-04-25 08:48:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

[feat] update config

Browse Source
This commit is contained in:
jingyaogong 2025-12-31 10:29:13 +08:00
parent 6242980917
commit eead9538b2
1 changed files with 4 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
scripts/convert_model.py
View File

@ -70,13 +70,9 @@ def convert_transformers2torch(transformers_path, torch_path):
if __name__ == '__main__':
lm_config = MiniMindConfig(hidden_size=768, num_hidden_layers=16, max_seq_len=8192, use_moe=False)
lm_config = MiniMindConfig(hidden_size=512, num_hidden_layers=8, max_seq_len=8192, use_moe=False)
torch_path = f"../out/full_sft_{lm_config.hidden_size}{'_moe' if lm_config.use_moe else ''}.pth"
transformers_path = '../MiniMind2'
transformers_path = '../MiniMind2-Small'
convert_torch2transformers_llama(torch_path, transformers_path)
# # # convert transformers to torch model
# # convert_transformers2torch(transformers_path, torch_path)
# # convert transformers to torch model
# convert_transformers2torch(transformers_path, torch_path)