8000 Rpan lisa more models by research4pan · Pull Request #742 · OptimalScale/LMFlow · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
8000
8000

Rpan lisa more models #742

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 4, 2024
Merged

Rpan lisa more models #742

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9bdd4f6
Add script to print model architecture
research4pan Apr 4, 2024
3b3b658
Add lisa support for gpt2
research4pan Apr 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions scripts/tools/print_model_architecture.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
#!/usr/bin/env python
#coding=utf-8
import argparse
import sys
from transformers import AutoModel

def parse_argument(sys_argv):
parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument("--model_name_or_path", type=str, default='gpt2')
args = parser.parse_args(sys_argv[1:])
return args

def main():
args = parse_argument(sys.argv)
model_name = args.model_name_or_path
model = AutoModel.from_pretrained(model_name)

print(model.config)
print(model)

if __name__ == "__main__":
main()
6 changes: 6 additions & 0 deletions src/lmflow/args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -591,6 +591,12 @@ class FinetunerArguments(TrainingArguments):
"help": "the number of steps in each freezing interval of LISA, i.e. the selected unfreezed layers are randomly switched every {lisa_interval_steps} steps."
}
)
lisa_layers_attribute: int = field(
default="model.model.layers",
metadata={
"help": "where the layer attribute stores, e.g. model.model.layers"
}
)


@dataclass
Expand Down
6 changes: 5 additions & 1 deletion src/lmflow/pipeline/finetuner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -311,10 +311,14 @@ def __init__(self, n_layers, interval_steps, model):
self.layers_attribute = 'model.model.layers' # Layer access path for Qwen model
elif self.model.__class__.__name__ == 'MistralForCausalLM':
self.layers_attribute = 'model.model.layers'
elif self.model.__class__.__name__ == 'MixtralForCausalLM':
self.layers_attribute = 'model.model.layers'
elif self.model.__class__.__name__ == 'GemmaForCausalLM':
self.layers_attribute = 'model.model.layers'
elif self.model.__class__.__name__ == 'GPT2LMHeadModel':
self.layers_attribute = 'model.transformer.h'
else:
self.layers_attribute = 'model.transformer.h' # General access path
self.layers_attribute = training_args.lisa_layers_attribute
self.total_layers = len(eval('self.' + self.layers_attribute)) # Dynamically execute to get the number of layers

self.active_layers_indices = []
Expand Down
0