Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Sign in / Register
Toggle navigation
B
Basedformer
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Locked Files
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Security & Compliance
Security & Compliance
Dependency List
License Compliance
Packages
Packages
List
Container Registry
Analytics
Analytics
CI / CD
Code Review
Insights
Issues
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
novelai-storage
Basedformer
Commits
773e886f
Commit
773e886f
authored
Apr 06, 2022
by
novelailab
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
some more cleanup
parent
09e4a19b
Changes
10
Hide whitespace changes
Inline
Side-by-side
Showing
10 changed files
with
3 additions
and
3 deletions
+3
-3
lm_arch/lm_base.py
lm_arch/lm_base.py
+0
-0
scripts/act_ck.py
scripts/act_ck.py
+0
-0
scripts/comparehf.py
scripts/comparehf.py
+2
-2
scripts/cudagraph.py
scripts/cudagraph.py
+0
-0
scripts/gelu_test.py
scripts/gelu_test.py
+0
-0
scripts/gpt2port.py
scripts/gpt2port.py
+0
-0
scripts/gptj.py
scripts/gptj.py
+0
-0
scripts/hfport.py
scripts/hfport.py
+0
-0
scripts/test.py
scripts/test.py
+0
-0
train.py
train.py
+1
-1
No files found.
lm_arch/lm_
class
.py
→
lm_arch/lm_
base
.py
View file @
773e886f
File moved
act_ck.py
→
scripts/
act_ck.py
View file @
773e886f
File moved
comparehf.py
→
scripts/
comparehf.py
View file @
773e886f
from
lm_arch
import
lm_
class
from
lm_arch
import
lm_
base
from
lm_arch.utils
import
*
from
lm_arch.utils
import
*
import
time
import
time
...
@@ -67,7 +67,7 @@ def timeit(func, r=1, n=5, quiet=False, function=None, do_tqdm=False, first=True
...
@@ -67,7 +67,7 @@ def timeit(func, r=1, n=5, quiet=False, function=None, do_tqdm=False, first=True
with
torch
.
no_grad
():
with
torch
.
no_grad
():
based_model
=
lm_
class
.
load_gpt_j
()
.
cuda
()
.
half
()
.
eval
()
based_model
=
lm_
base
.
load_gpt_j
()
.
cuda
()
.
half
()
.
eval
()
based_model
=
based_model
.
lm
based_model
=
based_model
.
lm
print
(
"Loaded based model"
)
print
(
"Loaded based model"
)
hf_model
=
no_init
(
lambda
:
AutoModelForCausalLM
.
from_pretrained
(
'/home/xuser/models/j6b_ckpt_14001'
))
.
cuda
()
.
half
()
.
eval
()
hf_model
=
no_init
(
lambda
:
AutoModelForCausalLM
.
from_pretrained
(
'/home/xuser/models/j6b_ckpt_14001'
))
.
cuda
()
.
half
()
.
eval
()
...
...
cudagraph.py
→
scripts/
cudagraph.py
View file @
773e886f
File moved
gelu_test.py
→
scripts/
gelu_test.py
View file @
773e886f
File moved
gpt2port.py
→
scripts/
gpt2port.py
View file @
773e886f
File moved
gptj.py
→
scripts/
gptj.py
View file @
773e886f
File moved
hfport.py
→
scripts/
hfport.py
View file @
773e886f
File moved
test.py
→
scripts/
test.py
View file @
773e886f
File moved
train.py
View file @
773e886f
...
@@ -6,7 +6,7 @@ import torch.optim as optim
...
@@ -6,7 +6,7 @@ import torch.optim as optim
from
pathlib
import
Path
from
pathlib
import
Path
from
lm_train
import
optimizer
,
utils
from
lm_train
import
optimizer
,
utils
from
torch.utils
import
data
from
torch.utils
import
data
from
main
import
*
from
lm_arch
import
lm_base
import
yaml
import
yaml
import
sys
import
sys
from
tqdm
import
tqdm
from
tqdm
import
tqdm
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment