kanshan/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-04-23 15:58:15 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

[update] default model

Browse Source
This commit is contained in:
jingyaogong 2026-03-31 13:40:16 +08:00
parent b1865f75c2
commit b7e0ae21d6
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/convert_model.py
View File

@ -126,10 +126,10 @@ def convert_json_to_jinja(json_file_path, output_path):
if __name__ == '__main__':
lm_config = MiniMindConfig(hidden_size=768, num_hidden_layers=8, max_seq_len=8192, use_moe=True)
lm_config = MiniMindConfig(hidden_size=768, num_hidden_layers=8, max_seq_len=8192, use_moe=False)
# convert torch to transformers
torch_path = f"../out/full_sft_{lm_config.hidden_size}{'_moe' if lm_config.use_moe else ''}.pth"
transformers_path = '../minimind-3-moe'
transformers_path = '../minimind-3'
convert_torch2transformers(torch_path, transformers_path)
# # merge lora