jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Fix] add bc for alignbench summarizer (#1306)

Browse Source 
* fix pip version

* fix pip version

* fix alignbench

* fix import error
This commit is contained in:
bittersweet1999 2024-07-12 11:06:20 +08:00 committed by GitHub
parent 62f55987f1
commit 8e7ad2e981
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/datasets/subjective/multiround/mtbench_single_judge_diff_temp.py
View File

@ -26,7 +26,7 @@ for _name in subjective_all_sets:
template="""{dialogue}""", template="""{dialogue}""",
), ),
retriever=dict(type=ZeroRetriever), retriever=dict(type=ZeroRetriever),
inferencer=dict(type=ChatInferencer, max_seq_len=4096, max_out_len=512, temperature=temperature, do_sample=do_sample,infer_mode='every'), inferencer=dict(type=ChatInferencer, max_seq_len=4096, max_out_len=1024, temperature=temperature, do_sample=do_sample,infer_mode='every'),
) )
subjective_eval_cfg = dict( subjective_eval_cfg = dict(

1
opencompass/cli/main.py
View File

@ -1,6 +1,7 @@
# flake8: noqa # flake8: noqa
# yapf: disable # yapf: disable
import argparse import argparse
import copy
import getpass import getpass
import os import os
import os.path as osp import os.path as osp

3
opencompass/summarizers/subjective/alignmentbench.py
View File

@ -369,6 +369,9 @@ class AlignmentBenchSummarizer:
if os.path.isdir(subdir_path): if os.path.isdir(subdir_path):
judged_answers, references = get_judgeanswer_and_reference( judged_answers, references = get_judgeanswer_and_reference(
dataset, subdir_path, self.judge_function) dataset, subdir_path, self.judge_function)
if len(judged_answers) == 0:
score_by_judgemodel[model] = None
continue
if self.judge_type == 'general': if self.judge_type == 'general':
get_dimension_results(judged_answers, references, fout, get_dimension_results(judged_answers, references, fout,
fout_flag, model) fout_flag, model)