Closed RonanKMcGovern closed 11 months ago
hi @RonanKMcGovern thanks for your issue I ran:
import torch
from transformers import AutoModelForCausalLM
model_id = "tiiuae/falcon-7b"
model = AutoModelForCausalLM.from_pretrained(
model_id,
load_in_4bit=True,
torch_dtype=torch.bfloat16,
)
for n, p in model.named_parameters():
if p.device.type == "meta":
print(f"{n} is on meta!")
and I can confirm I had no parameter on the meta device while having the same error message you shared. Perhaps it is a bug at accelerate. Can you file an issue there and use this small handy snippet?
done, thanks: https://github.com/huggingface/accelerate/issues/2103
System Info
A6000 GPU on runpod.
Copy-and-paste the text below in your GitHub issue and FILL OUT the two last points.
transformers
version: 4.35.0.dev0Who can help?
@ArthurZucker @younesbelkada
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction
Expected behavior
I would expect this model to easily fit on an A6000 with 48GB of VRAM.
Instead, I get this error/notification: