Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
fix(agent): treat empty HF_TOKEN as no token to avoid empty Bearer header (#264)
Albertb339c0d664ec
diff --git a/laya/agent.py b/laya/agent.pyindex 9a9f59c4..a002891d 100644--- a/laya/agent.py+++ b/laya/agent.py@@ -185,7 +185,7 @@ class Agent:# checkpoints, which an unfiltered snapshot would unnecessarily download.prefix = f"{subfolder}/" if subfolder else ""kw = {- "token": token or os.environ.get("HF_TOKEN"),+ "token": token or os.environ.get("HF_TOKEN") or None,"allow_patterns": [prefix + name for name in ("rl_agent_config.json", "model.safetensors", "tokenizer/*", "encoder/*",)],