Merge branch 'main' of https://github.com/sotopia-lab/sotopia-llm-ft …

…into feature/selftrain-data-generation

.gitignore

@@ -5,6 +5,13 @@ __pycache__
 dist
 .venv
 
+# Byte-compiled / optimized / DLL files
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
 # Log
 *.log
 *.log.*
@@ -13,6 +20,7 @@ llm_ft/checkpoints/*
 llm_ft/*_checkpoints/*
 !**/dummy_conversation.json
 !llm_ft/deepspeed_config_s2.json
+!llm_rl/data/*.json
 
 # Editor
 .idea
@@ -33,4 +41,161 @@ tests/state_of_the_union.txt
 
 # Build
 build
-!dummy_file
+!dummy_file
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+./llm_rl/preprocess/GPT4-4_Redis_Easy_No_Slide
+
+llm_rl/*cache/

README.md

@@ -2,9 +2,9 @@
 
 We split our overall framework into multiple parts
 
+0. Data Generate --> Input None / Output new data on redis
 1. Data Processing --> Output general form of sotopia train and test data
 2. Together AI Finetuning --> Input the train and test data / Output model checkpoint
 3. LLM Finetuning --> Input the train and test data / Output model checkpoint
 4. LLM Deplyment --> Input LLM Finetuned model checkpoint / Output Deployable OpenAI type API
-5. Eval --> Input model checkpoint / Output evaluation scores
-6. Generate --> Input None / Output new data on redis
+5. Eval --> Input model checkpoint / Output evaluation scores

data_generate/README.md

@@ -0,0 +1,20 @@
+# Data Generation
+
+For the first step, we generate envProfile (including scenario / social goal / relationship restriction) based on inspiring prompt.
+
+For the 2.1 step, we put the original agentProfile and relationshipProfile into our new redis database
+
+For the 2.2 step, we combine them together to be combos based on conditiona sampling (the restriction is the relationship)
+
+All the EnvProfile (new generated), AgentProfile (sotopia original), RelationshipProfile (sotopia original), and envagentcombo are on the redis database that is new created.
+
+For the third step, we need to use another version of redis and convert it into json file and save the whole data in the database on the local machine.
+
+For the final step, we convert the whole thing into Ruiyi's format.
+
+# Local Redis Setting
+Since the redis-server cannot directly input json data, it requires loading a RedisJson model into the redis-server to enable this function. Therefore, we need to load a docker based on RedisJson:
+
+docker run -p 6379:6379 --name redis-stack redis/redis-stack:latest
+
+Link: <https://github.com/RedisJSON/RedisJSON>