Skip to content
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

remove duplicate model converter script #13

Merged
merged 2 commits into from
Jun 22, 2023
Merged

remove duplicate model converter script #13

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
3e45c1c
remove constraints on model name
lvhan028 Jun 22, 2023
6e6e182
remove duplicate model converter
lvhan028 Jun 22, 2023
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
210 changes: 0 additions & 210 deletions examples/cpp/llama/llama_ckpt_convert.py
View file
Open in desktop

This file was deleted.

11 changes: 1 addition & 10 deletions llmdeploy/serve/fastertransformer/deploy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,6 @@
import torch
from sentencepiece import SentencePieceProcessor

supported_models = [
'vicuna-7b', 'vicuna-13b', 'llama-7b', 'llama-13b', 'llama-30b',
'llama-65b'
]
supported_formats = ['llama', 'hf']


Expand Down Expand Up @@ -379,18 +375,14 @@ def main(model_name: str,

Args:
model_name (str): the name of the to-be-deployed model, such as
llama-7b, llama-13b and etc
llama-7b, llama-13b, vicuna-7b and etc
model_path (str): the directory path of the model
model_format (str): the format of the model, fb or hf. 'fb' stands for
META's llama format, and 'hf' means huggingface format
tokenizer_path (str): the path of tokenizer model
dst_path (str): the destination path that saves outputs
tp (int): the number of GPUs used for tensor parallelism
"""
if model_name.lower() not in supported_models:
print(f'"{model_name}" is not supported. The supported models are: '
f'{supported_models}')
exit(-1)

if model_format not in supported_formats:
print(f'the model format "{model_format}" is not supported. '
Expand All @@ -409,7 +401,6 @@ def main(model_name: str,
if triton_models_path is None:
exit(-1)

model_name = model_name.lower()
if model_format == 'llama':
res = deploy_llama(model_name, model_path, tokenizer_path,
triton_models_path, tp)
Expand Down