add safetensor

eval.py

@@ -2,6 +2,7 @@ import gymnasium as gym
 import json
 from stable_baselines3 import SAC
 from stable_baselines3.common.evaluation import evaluate_policy
+from safetensors.torch import save_file
 
 if __name__ == "__main__":
 
@@ -11,6 +12,10 @@ if __name__ == "__main__":
     
     agent = SAC.load("model.zip")
     
+    # Save the state dict as a safetensors file
+    policy_state_dict = agent.policy.state_dict()
+    save_file(policy_state_dict, "model.safetensors")
+
     mean_reward, std_reward = evaluate_policy(agent, env, n_eval_episodes=n_eval_episodes, deterministic=deterministic)
     
     print(f"reward : {mean_reward} +/- {std_reward}")

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cf5c38b9e704f1bda8409a53a752c8d38e2ffbe6b2ac7484c05be31bfe1722
+size 1451688