update gpt-3.5-turbo to gpt-4o-mini

sotopia-lab · Oct 1, 2024 · 1923c18 · 1923c18
1 parent a73ff48
commit 1923c18
Show file tree

Hide file tree

Showing 14 changed files with 28 additions and 28 deletions.
diff --git a/README.md b/README.md
@@ -74,8 +74,8 @@ asyncio.run(
     run_async_server(
         model_dict={
             "env": "gpt-4",
-            "agent1": "gpt-3.5-turbo",
-            "agent2": "gpt-3.5-turbo",
+            "agent1": "gpt-4o-mini",
+            "agent2": "gpt-4o-mini",
         },
         sampler=UniformSampler(),
     )

diff --git a/docs/pages/concepts/agents.md b/docs/pages/concepts/agents.md
@@ -11,7 +11,7 @@ class LLMAgent(BaseAgent[Observation, AgentAction]):
         agent_name: str | None = None,
         uuid_str: str | None = None,
         agent_profile: AgentProfile | None = None,
-        model_name: str = "gpt-3.5-turbo",
+        model_name: str = "gpt-4o-mini",
         script_like: bool = False,
     ) -> None:
 ```
@@ -26,7 +26,7 @@ class ScriptWritingAgent(LLMAgent):
         agent_name: str | None = None,
         uuid_str: str | None = None,
         agent_profile: AgentProfile | None = None,
-        model_name: str = "gpt-3.5-turbo",
+        model_name: str = "gpt-4o-mini",
         agent_names: list[str] = [],
         background: ScriptBackground | None = None,
     ) -> None:

diff --git a/docs/pages/index.mdx b/docs/pages/index.mdx
@@ -206,8 +206,8 @@ asyncio.run(
     run_async_server(
         model_dict={
             "env": "gpt-4",
-            "agent1": "gpt-3.5-turbo",
-            "agent2": "gpt-3.5-turbo",
+            "agent1": "gpt-4o-mini",
+            "agent2": "gpt-4o-mini",
         },
         sampler=UniformSampler(),
     )

diff --git a/examples/benchmark_evaluator.py b/examples/benchmark_evaluator.py
@@ -15,8 +15,8 @@
 
 target_model_patterns: list[list[str]] = [
     ["gpt-4", "gpt-4", "gpt-3.5-turbo"],
-    ["gpt-4", "gpt-3.5-turbo", "gpt-4"],
-    ["gpt-4", "gpt-3.5-turbo", "togethercomputer/llama-2-70b-chat"],
+    ["gpt-4", "gpt-4o-mini", "gpt-4"],
+    ["gpt-4", "gpt-4o-mini", "togethercomputer/llama-2-70b-chat"],
     ["gpt-4", "togethercomputer/llama-2-70b-chat", "gpt-3.5-turbo"],
 ]
 

diff --git a/examples/experiment_eval.py b/examples/experiment_eval.py
@@ -170,8 +170,8 @@ def run_async_server_in_batch(
     batch_size: int = 1,
     model_names: dict[str, LLM_Name] = {
         "env": "gpt-4",
-        "agent1": "gpt-3.5-turbo",
-        "agent2": "gpt-3.5-turbo",
+        "agent1": "gpt-4o-mini",
+        "agent2": "gpt-4o-mini",
     },
     tag: str | None = None,
     verbose: bool = False,

diff --git a/examples/fix_missing_episodes.py b/examples/fix_missing_episodes.py
@@ -252,8 +252,8 @@ def re_run_missing_episodes(
     combo_with_models: dict[tuple[LLM_Name, LLM_Name], list[tuple[str, str, str]]],
     model_names: dict[str, LLM_Name] = {
         "env": "gpt-4",
-        "agent1": "gpt-3.5-turbo",
-        "agent2": "gpt-3.5-turbo",
+        "agent1": "gpt-4o-mini",
+        "agent2": "gpt-4o-mini",
     },
     batch_size: int = 5,
     verbose: bool = False,

diff --git a/examples/fix_missing_episodes_with_tag.py b/examples/fix_missing_episodes_with_tag.py
@@ -350,8 +350,8 @@ def re_run_missing_episodes(
     env_agent_ids: List[Tuple[str, str, str]] = [],
     model_names: dict[str, LLM_Name] = {
         "env": "gpt-4",
-        "agent1": "gpt-3.5-turbo",
-        "agent2": "gpt-3.5-turbo",
+        "agent1": "gpt-4o-mini",
+        "agent2": "gpt-4o-mini",
     },
     batch_size: int = 5,
     rerun_tag: str = "missing_episodes",

diff --git a/examples/generate_script.py b/examples/generate_script.py
@@ -175,7 +175,7 @@ def full_freeform(
 def run_async_server_in_batch_script(
     *,
     batch_size: int = 10,
-    model: LLM_Name = "gpt-3.5-turbo",
+    model: LLM_Name = "gpt-4o-mini",
     tag: str | None = None,
     push_to_db: bool = True,
     json_in_script: bool = False,

diff --git a/examples/minimalist_demo.py b/examples/minimalist_demo.py
@@ -28,8 +28,8 @@
     run_async_server(
         model_dict={
             "env": "gpt-4",
-            "agent1": "gpt-3.5-turbo",
-            "agent2": "gpt-3.5-turbo",
+            "agent1": "gpt-4o-mini",
+            "agent2": "gpt-4o-mini",
         },
         sampler=UniformSampler(),
     )

diff --git a/sotopia/agents/generate_agent_background.py b/sotopia/agents/generate_agent_background.py
@@ -20,13 +20,13 @@ async def generate_background(
     else:
         initial_profile = str(basic_info)
         profile = await agenerate_init_profile(
-            model_name="gpt-3.5-turbo", basic_info=basic_info
+            model_name="gpt-4o-mini", basic_info=basic_info
         )
         first_narrative = convert_narratives(
-            model_name="gpt-3.5-turbo", narrative="first", text=profile
+            model_name="gpt-4o-mini", narrative="first", text=profile
         )
         second_narrative = convert_narratives(
-            model_name="gpt-3.5-turbo", narrative="second", text=profile
+            model_name="gpt-4o-mini", narrative="second", text=profile
         )
         previous_messages = []
     return (
@@ -67,8 +67,8 @@ def generate_background_conversation(
         json.dump(background_dict, f, indent=4)
 
     model_names: dict[str, str] = {
-        "env": "gpt-3.5-turbo",
-        "agent2": "gpt-3.5-turbo",
+        "env": "gpt-4o-mini",
+        "agent2": "gpt-4o-mini",
         "agent1": "gpt-4",
     }
 

diff --git a/sotopia/agents/llm_agent.py b/sotopia/agents/llm_agent.py
@@ -27,7 +27,7 @@ def __init__(
         agent_name: str | None = None,
         uuid_str: str | None = None,
         agent_profile: AgentProfile | None = None,
-        model_name: str = "gpt-3.5-turbo",
+        model_name: str = "gpt-4o-mini",
         script_like: bool = False,
     ) -> None:
         super().__init__(
@@ -99,7 +99,7 @@ def __init__(
         agent_name: str | None = None,
         uuid_str: str | None = None,
         agent_profile: AgentProfile | None = None,
-        model_name: str = "gpt-3.5-turbo",
+        model_name: str = "gpt-4o-mini",
         agent_names: list[str] = [],
         background: ScriptBackground | None = None,
     ) -> None:

diff --git a/sotopia/envs/parallel.py b/sotopia/envs/parallel.py
@@ -130,7 +130,7 @@ def __init__(
             ["none", "speak", "non-verbal communication", "action", "leave"]
         ),
         action_order: Literal["simultaneous", "round-robin", "random"] = "simultaneous",
-        model_name: str = "gpt-3.5-turbo",
+        model_name: str = "gpt-4o-mini",
         evaluators: list[Evaluator] = [],
         terminal_evaluators: list[Evaluator] = [],
         uuid_str: str | None = None,

diff --git a/sotopia/generation_utils/generate.py b/sotopia/generation_utils/generate.py
@@ -43,7 +43,7 @@
     "together_ai/meta-llama/Llama-3-8b-chat-hf",
     "together_ai/meta-llama/Llama-3-70b-chat-hf",
     "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
-    "gpt-3.5-turbo",
+    "gpt-4o-mini",
     "gpt-3.5-turbo-16k-0613",
     "gpt-3.5-turbo-finetuned",
     "gpt-3.5-turbo-ft-MF",
@@ -281,7 +281,7 @@ def _type(self) -> str:
 
 def _return_fixed_model_version(model_name: str) -> str:
     if model_name in [
-        "gpt-3.5-turbo",
+        "gpt-4o-mini",
         "gpt-3.5-turbo-finetuned",
         "gpt-3.5-turbo-ft-MF",
         "gpt-4",

diff --git a/sotopia_conf/server_conf/server.gin b/sotopia_conf/server_conf/server.gin
@@ -9,7 +9,7 @@ PUSH_TO_DB=False
 OMNISCIENT=False
 
 server.run_async_server:
-    model_dict={"env": "gpt-4", "agent1": "gpt-3.5-turbo", "agent2": "gpt-3.5-turbo"}
+    model_dict={"env": "gpt-4", "agent1": "gpt-4o-mini", "agent2": "gpt-3.5-turbo"}
     action_order=%ACTION_ORDER
     push_to_db=%PUSH_TO_DB
     using_async=True