webarena/xiangyi-li · BenchFlow

.github
-
fix type errors
2 years ago
.gitignore
2.21 kB
minor
2 years ago
.pre-commit-config.yaml
638 B
add instruction for self-hosting webarena
3 years ago
CITATION.cff
353 B
Create CITATION.cff
3 years ago
LICENSE
11.4 kB
release commit
3 years ago
README.md
8.12 kB
Update README.md
2 years ago
agent
-
fix typo
3 years ago
browser_env
-
fix the regex in cleaning axtree
2 years ago
check_errors.sh
814 B
release commit
3 years ago
config_files
-
remove duplicate "string_match" in "eval_types" for task 301 302
2 years ago
environment_docker
-
Update README.md Minor environment setup update
2 years ago
evaluation_harness
-
fix type errors
2 years ago
llms
-
fix type errors
2 years ago
media
-
add v2 execution trajectories
2 years ago
minimal_example.py
4.62 kB
Update tests configs to fit the current settings
3 years ago
parallel_run.sh
2.53 kB
add parallel running script
3 years ago
prepare.sh
120 B
release commit
3 years ago
requirements.txt
156 B
add openai and transformers lib version
2 years ago
resources
-
add v2 execution trajectories
2 years ago
run.py
14.5 kB
minor
2 years ago
scripts
-
minor
2 years ago
setup.cfg
369 B
update README
3 years ago
setup.py
69 B
release commit
3 years ago
tests
-
Merge remote-tracking branch 'origin/main' into new_eval
2 years ago