423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

support llama pro #2338 , add rslora

Browse Source
This commit is contained in:
hiyouga
2024-02-15 02:27:36 +08:00
parent 8a1b389086
commit 7924ffc55d
24 changed files with 438 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/llamafy_internlm2.py
View File

@@ -1,6 +1,6 @@
# coding=utf-8
# Converts the InternLM2 model in the same format as LLaMA2.
# Usage: python llamafy_internlm2.py --input_dir input --output_dir output --shard_size 10GB
# Usage: python llamafy_internlm2.py --input_dir input --output_dir output
# Warning: We have found that the converted model cannot infer correctly. It will be fixed later.
import json
@@ -98,7 +98,9 @@ def save_config(input_dir: str, output_dir: str):
print("Model config saved in {}".format(os.path.join(output_dir, CONFIG_NAME)))
def llamafy_internlm2(input_dir: str, output_dir: str, shard_size: str, save_safetensors: Optional[bool] = False):
def llamafy_internlm2(
input_dir: str, output_dir: str, shard_size: Optional[str] = "2GB", save_safetensors: Optional[bool] = False
):
try:
os.makedirs(output_dir, exist_ok=False)
except Exception as e: