ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support llama pro #2338 , add rslora

Browse Source 
Former-commit-id: 40d659b7f30dd5a004703c176ec1f22dc864e505
This commit is contained in:
hiyouga
2024-02-15 02:27:36 +08:00
parent b403f8d8a8
commit 596b6828cb
24 changed files with 438 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/llamafy_qwen.py
View File

@@ -1,6 +1,6 @@
# coding=utf-8
# Converts the Qwen models in the same format as LLaMA2.
# Usage: python llamafy_qwen.py --input_dir input --output_dir output --shard_size 10GB
# Usage: python llamafy_qwen.py --input_dir input --output_dir output
# Converted model: https://huggingface.co/hiyouga/Qwen-14B-Chat-LLaMAfied
import json
@@ -128,7 +128,9 @@ def save_config(input_dir: str, output_dir: str, torch_dtype: str):
print("Model config saved in {}".format(os.path.join(output_dir, CONFIG_NAME)))
def llamafy_qwen(input_dir: str, output_dir: str, shard_size: str, save_safetensors: Optional[bool] = False):
def llamafy_qwen(
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: