starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-20 16:35:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support

Browse Source
This commit is contained in:
yangapku
2023-11-30 15:29:13 +08:00
parent 981c89b2a9
commit e8e15962d8
52 changed files with 6139 additions and 1435 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
finetune.py
View File

@@ -278,11 +278,11 @@ def train():
local_rank = training_args.local_rank
device_map = None
device_map = "auto"
world_size = int(os.environ.get("WORLD_SIZE", 1))
ddp = world_size != 1
if lora_args.q_lora:
device_map = {"": int(os.environ.get("LOCAL_RANK") or 0)} if ddp else None
device_map = {"": int(os.environ.get("LOCAL_RANK") or 0)} if ddp else "auto"
if len(training_args.fsdp) > 0 or deepspeed.is_deepspeed_zero3_enabled():
logging.warning(
"FSDP or ZeRO3 are not incompatible with QLoRA."