FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[Original HTTPS Page]
nla-groot/scripts/eval at main · CodCodingCode/nla-groot · GitHub
CodCodingCode
/
nla-groot
Public
Notifications
You must be signed in to change notification settings
Fork
0
Star
1
Code
Issues
0
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
nla-groot
/
scripts
/
eval
/
Copy path
Directory actions
More options
More options
Directory actions
More options
More options
Latest commit
History
History
History
Breadcrumbs
nla-groot
/
scripts
/
eval
/
Copy path
Folders and files
Name
Name
Last commit message
Last commit date
parent directory
..
diag
diag
_post_sft_evals_helpers.py
_post_sft_evals_helpers.py
ab_sweep_compare.sh
ab_sweep_compare.sh
action_consistency_smoke.py
action_consistency_smoke.py
action_effect_probe.py
action_effect_probe.py
action_effect_probe_batched.py
action_effect_probe_batched.py
aggregate_sim_cache.py
aggregate_sim_cache.py
audit_bullet_informativeness.py
audit_bullet_informativeness.py
audit_diversity.py
audit_diversity.py
audit_hard_negatives.py
audit_hard_negatives.py
audit_prompt_hardening.py
audit_prompt_hardening.py
audit_ptype_disambiguation.py
audit_ptype_disambiguation.py
auto_cf_eval_after_sft.sh
auto_cf_eval_after_sft.sh
av_caption_intent_diff.py
av_caption_intent_diff.py
build_eval_cases.py
build_eval_cases.py
build_grpo_steer_scorecard.py
build_grpo_steer_scorecard.py
build_improvements_report.py
build_improvements_report.py
build_sa9_judge_report.py
build_sa9_judge_report.py
build_v3_scorecard.py
build_v3_scorecard.py
build_v4_extraction_scorecard.py
build_v4_extraction_scorecard.py
build_v4_per_suite_view.py
build_v4_per_suite_view.py
build_wandb_workspace.py
build_wandb_workspace.py
build_wandb_workspace_grpo.py
build_wandb_workspace_grpo.py
cache_libero_init_states.py
cache_libero_init_states.py
check_groot_env.py
check_groot_env.py
closed_loop_av_capture.py
closed_loop_av_capture.py
closed_loop_retrieval.py
closed_loop_retrieval.py
closed_loop_sim_ab.py
closed_loop_sim_ab.py
compare_cf_steer_checkpoints.py
compare_cf_steer_checkpoints.py
compare_judge_runs.py
compare_judge_runs.py
decide_consistency_ab.py
decide_consistency_ab.py
default_steer_boot.txt
default_steer_boot.txt
diff_scorecards.py
diff_scorecards.py
dump_av_samples.py
dump_av_samples.py
eval_protocol.md
eval_protocol.md
extract_attributes.py
extract_attributes.py
extract_label_frames.py
extract_label_frames.py
health_check_steer_server.py
health_check_steer_server.py
judge_prompt.md
judge_prompt.md
launch_cf_steer_film.sh
launch_cf_steer_film.sh
launch_steer_server.sh
launch_steer_server.sh
llm_judge_av_captions.py
llm_judge_av_captions.py
log_eval_to_wandb.py
log_eval_to_wandb.py
make_pilot_pair_videos.sh
make_pilot_pair_videos.sh
make_v1_vs_v3_grid.sh
make_v1_vs_v3_grid.sh
nla_steer_alpha_sweep.py
nla_steer_alpha_sweep.py
nla_steer_ar_smoke.py
nla_steer_ar_smoke.py
nla_steer_groot_action.py
nla_steer_groot_action.py
nla_steer_leverage_sweep.py
nla_steer_leverage_sweep.py
nla_steer_overlay_video.py
nla_steer_overlay_video.py
nla_steer_overlay_visual_demo.py
nla_steer_overlay_visual_demo.py
nla_steer_quant_probe.py
nla_steer_quant_probe.py
overlay_av_video.py
overlay_av_video.py
per_config_noise_probe.py
per_config_noise_probe.py
play.sh
play.sh
play_repl.py
play_repl.py
plot_retrieval_cosines.py
plot_retrieval_cosines.py
plot_v9_implementation_charts.py
plot_v9_implementation_charts.py
populate_no_steer_cache.py
populate_no_steer_cache.py
probe_extraction_sweep.py
probe_extraction_sweep.py
probe_h_attributes.py
probe_h_attributes.py
probe_h_freebies.py
probe_h_freebies.py
prompt_mode_side_eval.py
prompt_mode_side_eval.py
rubric.py
rubric.py
run_gr00t_server_nla_steer.py
run_gr00t_server_nla_steer.py
run_grpo_steer_holdout.sh
run_grpo_steer_holdout.sh
run_interp_panel.py
run_interp_panel.py
run_llm_judge.py
run_llm_judge.py
run_post_sft_evals.sh
run_post_sft_evals.sh
run_post_sft_evals_v4.sh
run_post_sft_evals_v4.sh
sa2_pilot_v4_spatial_judge.py
sa2_pilot_v4_spatial_judge.py
score_panel.py
score_panel.py
steer_server_status.sh
steer_server_status.sh
steerability_eval.py
steerability_eval.py
steerability_smoke.yaml
steerability_smoke.yaml
steerability_v1.yaml
steerability_v1.yaml
steerability_v1_vs_v3.yaml
steerability_v1_vs_v3.yaml
stop_steer_server.sh
stop_steer_server.sh
summarize_alpha_sweep.py
summarize_alpha_sweep.py
v4_extraction_diag.py
v4_extraction_diag.py
verify_libero_label_quality.py
verify_libero_label_quality.py
Back
|
FazBrowse Home
|
New Git URL