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

Refactor model conversion #296

Merged
merged 27 commits into from
Nov 3, 2023
Merged

Refactor model conversion #296

Show file tree
Hide file tree
Changes from 16 commits
Commits
Show all changes
27 commits
Select commit Hold shift + click to select a range
19ed1f9
split deploy.py
irexyc Oct 19, 2023
10e3884
fix get_cuda_tensor
irexyc Oct 19, 2023
b5d4ece
deploy qwen_awq
irexyc Oct 23, 2023
8c457a0
fix lint
irexyc Oct 23, 2023
edc60dd
add docstring
irexyc Oct 23, 2023
36c6f35
fix
irexyc Oct 25, 2023
43b350a
support baichuan/baichuan-awq
irexyc Oct 25, 2023
0985fbe
parameterizing size_per_head
irexyc Oct 30, 2023
e6f1b2c
remove try/except
irexyc Oct 30, 2023
cd6f01a
limit input model_format
irexyc Oct 31, 2023
b0146c0
add quant_path param
irexyc Oct 31, 2023
44be235
remove old deploy.py
irexyc Oct 31, 2023
a4101db
fix path
irexyc Oct 31, 2023
36a0f1a
fix transformer layer range when load bins
irexyc Nov 1, 2023
f1e4456
fix qwen init
irexyc Nov 1, 2023
db39b68
split & save log
irexyc Nov 1, 2023
4617668
relative import
irexyc Nov 1, 2023
0449c69
update get_config
irexyc Nov 1, 2023
e65127c
WeightFileMgr -> Reader
irexyc Nov 1, 2023
2a0405c
rename
irexyc Nov 1, 2023
c8fe088
update
irexyc Nov 1, 2023
f80a4c8
fix init_layer_id
irexyc Nov 1, 2023
b6255cb
rename llama.py -> meta_llama.py, hf.py -> llama.py
irexyc Nov 1, 2023
e092715
reduce code
irexyc Nov 1, 2023
dfc54d6
update arg description
irexyc Nov 2, 2023
794b620
fix meta llama
irexyc Nov 2, 2023
8224989
manually cleanup meta model params
irexyc Nov 2, 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
2 changes: 1 addition & 1 deletion lmdeploy/cli/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ def convert(self,
group_size (int): A parameter used in AWQ to quantize fp16 weights
to 4 bits.
"""
from lmdeploy.serve.turbomind.deploy import main as convert
from lmdeploy.turbomind.deploy.converter import main as convert

convert(model_name,
model_path,
Expand Down
Loading
Loading