Spaces:

vex-0
/

kinchat

Sleeping

App Files Files Community

340 kB

Ctrl+K

Ctrl+K

2 contributors

History: 6 commits

vex-0's picture

Task 13: GRPO training notebook (Unsloth + TRL, 17 cells, base-vs-trained eval, plot cells, push-to-Hub)

8e36acf 2 months ago

kinchat
Phase markers + restraint scoping: silent_witness/implicit_preference reward silence; secret_handling/multi_party expect engagement 2 months ago
notebooks
Task 13: GRPO training notebook (Unsloth + TRL, 17 cells, base-vs-trained eval, plot cells, push-to-Hub) 2 months ago
tests
Task 13: GRPO training notebook (Unsloth + TRL, 17 cells, base-vs-trained eval, plot cells, push-to-Hub) 2 months ago
.gitattributes

1.52 kB
initial commit 2 months ago
.gitignore

554 Bytes
Initial KinChat env: models, personas, scenarios, rubrics, grader, env loop, FastAPI app, client, dashboard, baseline inference (377 tests passing) 2 months ago
Dockerfile

525 Bytes
Initial KinChat env: models, personas, scenarios, rubrics, grader, env loop, FastAPI app, client, dashboard, baseline inference (377 tests passing) 2 months ago
README.md

4.09 kB
Fix HF Space metadata: colorFrom yellow, shorter description 2 months ago
inference.py

16.4 kB
Initial KinChat env: models, personas, scenarios, rubrics, grader, env loop, FastAPI app, client, dashboard, baseline inference (377 tests passing) 2 months ago
pyproject.toml

764 Bytes
Initial KinChat env: models, personas, scenarios, rubrics, grader, env loop, FastAPI app, client, dashboard, baseline inference (377 tests passing) 2 months ago