Skip to content

Actions: matee8/backtracking_llm

Actions

Publish Python 🐍 distribution 📦 to PyPI and TestPyPI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
65 workflow runs
65 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

chore(changelog): add new release to changelog
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #65: Commit 57d4015 pushed by matee8
46s v0.3.1
chore(changelog): add new release to changelog
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #64: Commit 57d4015 pushed by matee8
12s main
fix(tests/benchmark): remove obsolete test
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #63: Commit 16deceb pushed by matee8
22s main
fix(rl): cast str to path in operator
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #62: Commit f0336f3 pushed by matee8
1m 1s main
fix(benchmark): instantiate dictionary using built-in dict instead of…
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #61: Commit 730fc30 pushed by matee8
19s main
feat(benchmark): implement single-evalutation mode in runner
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #60: Commit e2cbec1 pushed by matee8
19s main
Merge branch 'main' of github.com:matee8/backtracking_llm
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #59: Commit ab108e4 pushed by matee8
16s main
fix(tests/rl): remove unused import from test_operators.py
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #58: Commit c065391 pushed by matee8
34s v0.3.0
fix(tests/rl): remove unused import from test_operators.py
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #57: Commit c065391 pushed by matee8
16s main
docs(changelog): document new changes in changelog
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #56: Commit 1ed5b5b pushed by matee8
16s main
fix(rl): align RlPolicyOperator observation space with training envir…
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #55: Commit b8db5ba pushed by matee8
14s main
fix(rl): set model to evaluation mode before running RL
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #54: Commit ee39298 pushed by matee8
1m 28s main
fix(rl): fix CUDA memory leak
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #53: Commit 9def9a4 pushed by matee8
15s main
fix(rl): fix pytest failures and pylint warnings
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #52: Commit ab24e75 pushed by matee8
16s main
feat(rl): add harsh penalty for empty generation
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #51: Commit 479683d pushed by matee8
15s main
feat(rl): apply ent_coef in PPO trainer
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #50: Commit 711fab8 pushed by matee8
13s main
fix(rl): add seed to unit test for data module
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #49: Commit a1dba1d pushed by matee8
17s main
test(rl): fix unit tests
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #48: Commit 06c9532 pushed by matee8
17s main
chore(rl): add configuration files to .gitignore
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #47: Commit 68746b3 pushed by matee8
16s main
feat(rl): add RL policy operator for executing trained policies
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #46: Commit 7dfef05 pushed by matee8
14s main
refactor(generation): extract generation logic to stateful class
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #45: Commit e1d0f62 pushed by matee8
23s main
fix(ci): install optional RL dependencies in CI workflows
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #44: Commit b798851 pushed by matee8
14s main
feat(rl): add judge LLM abstraction and OpenAI implementation
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #43: Commit 7ba143e pushed by matee8
14s main
Revert "feat(agents): create RLAgentOperator base"
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #42: Commit cbf94e6 pushed by matee8
15s main
docs(changelog): add v0.2.3 changelog
Publish Python 🐍 distribution 📦 to PyPI and TestPyPI #41: Commit 4f98fcb pushed by matee8
37s v0.2.3