Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
bbcdffb8
Commit
bbcdffb8
authored
Jan 12, 2024
by
daniel-furman
Browse files
remove system
parent
39a11d02
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
2 deletions
+3
-2
lm_eval/models/huggingface.py
lm_eval/models/huggingface.py
+3
-2
No files found.
lm_eval/models/huggingface.py
View file @
bbcdffb8
...
...
@@ -690,7 +690,7 @@ class HFLM(LM):
new_reqs
=
[]
for
req
in
requests
:
context
=
req
.
args
[
0
].
strip
()
system_prompt
=
"You are a helpful assistant."
#
system_prompt = "You are a helpful assistant."
# arc experiment with few-shot formatting
import
re
...
...
@@ -699,7 +699,8 @@ class HFLM(LM):
for
element
in
elements
[
1
:
-
1
]:
new_elements
.
append
(
element
.
strip
())
new_elements
chat
=
[{
"role"
:
"system"
,
"content"
:
system_prompt
}]
#chat = [{"role": "system", "content": system_prompt}]
chat
=
[]
for
i
in
range
(
len
(
new_elements
)):
if
i
%
2
==
0
:
chat
.
append
({
"role"
:
"user"
,
"content"
:
f
"Question:
{
new_elements
[
i
]
}
Answer:"
})
...
...
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