π The First Self-Improving agents with RL / Prompting Optimization
Python agentaigptmulti-agentpythonreinforcement-learningself-improvementsociety-of-mindswarm-intelligence
Restrict numpy version to 1.x since 2.0 crashes. (#27)
Dmitrii Khizbullin4eaca1a3d7e8
diff --git a/pyproject.toml b/pyproject.tomlindex 515680a..1c40123 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -62,8 +62,9 @@ tqdm = "^4.66.1"transformers = "^4.36.2"wikipedia = "^1.4.0"astunparse = "^1.6.3"-torch = "^2.1.0"+torch = ">=2.1.0, <=2.2.2"async-timeout = "^4.0.3"+numpy = "^1.25.2"[tool.poetry.group.dev.dependencies]pytest = "^8.0.2"