diff --git a/palm_rlhf_pytorch/__init__.py b/palm_rlhf_pytorch/__init__.py
index ecfa3a1..6399eda 100644
--- a/palm_rlhf_pytorch/__init__.py
+++ b/palm_rlhf_pytorch/__init__.py
@@ -1,3 +1,5 @@
 from palm_rlhf_pytorch.palm import PaLM
-from palm_rlhf_pytorch.reward import RewardModel
 from palm_rlhf_pytorch.ppo import RLHFTrainer, ActorCritic
+
+from palm_rlhf_pytorch.reward import RewardModel
+from palm_rlhf_pytorch.implicit_process_reward import ImplicitPRM
diff --git a/setup.py b/setup.py
index cc014a4..233bc98 100644
--- a/setup.py
+++ b/setup.py
@@ -3,7 +3,7 @@
 setup(
   name = 'PaLM-rlhf-pytorch',
   packages = find_packages(exclude=[]),
-  version = '0.3.1',
+  version = '0.3.2',
   license='MIT',
   description = 'PaLM + Reinforcement Learning with Human Feedback - Pytorch',
   author = 'Phil Wang',