Spaces:

ayushozha
/

replicalab

Running

App Files Files Community

replicalab / tests

368 kB

Ctrl+K

Ctrl+K

6 contributors

History: 22 commits

ayushozha's picture

Add local H100 scientist eval tooling

a29a83d 3 months ago

fixtures
Recover env judge training stack and sync project tracking 3 months ago
.gitkeep

1 Bytes
Complete FND 01 and FND 10, update task division with status tracking 3 months ago
test_api_rest_isolation.py

11.4 kB
Recover env judge training stack and sync project tracking 3 months ago
test_audit_contract.py

9.43 kB
Add ENV 09 disk persistence, OBS 07/09, TST 11 audit tests, close 10 Max tasks 3 months ago
test_cache.py

3.21 kB
Add hybrid Oracle layer and update architecture docs 3 months ago
test_client.py

12.9 kB
Recover env server client stack and deployment tracking 3 months ago
test_config.py

1.14 kB
Add MOD 11 typed StepInfo/RewardBreakdown and import completed foundation modules 3 months ago
test_env.py

31.9 kB
Add 12 scoring & environment improvements with full test coverage 3 months ago
test_integration.py

10 kB
Add 12 scoring & environment improvements with full test coverage 3 months ago
test_judge_policy.py

5.48 kB
Recover env judge training stack and sync project tracking 3 months ago
test_lab_manager_policy.py

29.8 kB
Recover env judge training stack and sync project tracking 3 months ago
test_llm_judge.py

6.28 kB
Add 12 scoring & environment improvements with full test coverage 3 months ago
test_local_eval.py

1.04 kB
Add local H100 scientist eval tooling 3 months ago
test_logging.py

15.6 kB
Add JDG 07: reward breakdown logging to CSV and JSONL per episode 3 months ago
test_mod08_schemas.py

28 kB
Add MOD 08 schema tests, V2 training stack, and close MOD 08/JDG 07/API 01/OBS 02 3 months ago
test_models.py

14.2 kB
Type EpisodeState and EpisodeLog with Protocol, ConversationEntry, RewardBreakdown (MOD 04) 3 months ago
test_notebooks.py

1.09 kB
Finalize demo flow and training assets 3 months ago
test_oracle.py

9.96 kB
Add hybrid Oracle layer and update architecture docs 3 months ago
test_prompts.py

2.98 kB
Add hybrid Oracle layer and update architecture docs 3 months ago
test_reward.py

22.9 kB
Recover env judge training stack and sync project tracking 3 months ago
test_rollout.py

9.06 kB
Recover env judge training stack and sync project tracking 3 months ago
test_rollout_traces.py

3.42 kB
Recover env judge training stack and sync project tracking 3 months ago
test_scenarios.py

10.1 kB
Add hybrid Oracle layer and update architecture docs 3 months ago
test_scientist_policy.py

32.5 kB
Add model-driven local runtime and dynamic demo flow 3 months ago
test_server.py

31.9 kB
Add model-driven local runtime and dynamic demo flow 3 months ago
test_training_cli.py

10.8 kB
Add local H100 scientist eval tooling 3 months ago
test_training_corpus.py

1.87 kB
Finalize demo flow and training assets 3 months ago
test_training_datasets.py

1.66 kB
Add 12 scoring & environment improvements with full test coverage 3 months ago
test_training_metrics.py

3.69 kB
Add 12 scoring & environment improvements with full test coverage 3 months ago
test_understanding.py

3.31 kB
Add 12 scoring & environment improvements with full test coverage 3 months ago
test_validation.py

12 kB
Recover env judge training stack and sync project tracking 3 months ago