Skip to content

Added support of google/flan models #2321

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

Closed
wangzhen263 wants to merge 10 commits into from
Closed

Added support of google/flan models #2321

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
f5d145b
Added a google/flan model adapter
wangzhen263 Aug 26, 2023
42b7cf5
flan model requires protobuf
wangzhen263 Aug 26, 2023
da73edd
flan model to compress model loader
wangzhen263 Aug 26, 2023
1c7f5fe
Merge branch 'lm-sys:main' into main
wangzhen263 Aug 26, 2023
2252f1a
Merge branch 'lm-sys:main' into main
wangzhen263 Aug 31, 2023
0a2d593
Merge branch 'lm-sys:main' into main
wangzhen263 Sep 1, 2023
b4ef47d
Added AutoModelForSeq2SeqLM to init google/flan models in 8bit
wangzhen263 Sep 1, 2023
d7bd21a
Merge pull request #1 from wangzhen263/flan-feature
wangzhen263 Sep 1, 2023
03efd2e
Fixed test error because of using isinstance() rather than type() for…
wangzhen263 Sep 1, 2023
061e69a
Fixed test error because of using isinstance() rather than type() for…
wangzhen263 Sep 1, 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
Prev Previous commit
Fixed test error because of using isinstance() rather than type() for… 
… a typecheck.
  • Loading branch information
@wangzhen263
wangzhen263 committed Sep 1, 2023
commit 061e69a2a5b1f2e3a508144d843f1c56d37a9efd
2 changes: 1 addition & 1 deletion fastchat/model/compression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,7 @@ def load_compress_model(model_path, device, torch_dtype, use_fast, revision="mai
# such as chatglm, chatglm2
try:
# google/flan-* models are based on an AutoModelForSeq2SeqLM.
if 'T5Config' in str(type(config))
if 'T5Config' in str(type(config)):
model = AutoModelForSeq2SeqLM.from_config(config, trust_remote_code=True)
else:
model = AutoModelForCausalLM.from_config(config, trust_remote_code=True)
Expand Down