(no commit message)

README.md

@@ -1,2 +0,0 @@
-# code-generator-trl-grpo
-

config.json

@@ -0,0 +1,6 @@
+{
+  "model": "openai//models/checkpoint-5",
+  "api_base": "https://modaic-ai--grpo-demo-serve.modal.run/v1",
+  "max_tokens": 1024,
+  "temperature": 0.7
+}

program.json

@@ -0,0 +1,39 @@
+{
+  "answer_question": {
+    "traces": [],
+    "train": [],
+    "demos": [],
+    "signature": {
+      "instructions": "Given the fields `query`, produce the fields `code`.",
+      "fields": [
+        {
+          "prefix": "Query:",
+          "description": "${query}"
+        },
+        {
+          "prefix": "Code:",
+          "description": "${code}"
+        }
+      ]
+    },
+    "lm": {
+      "model": "openai//models/checkpoint-5",
+      "model_type": "chat",
+      "cache": true,
+      "num_retries": 3,
+      "finetuning_model": null,
+      "launch_kwargs": {},
+      "train_kwargs": {},
+      "temperature": 0.7,
+      "max_tokens": 1024,
+      "api_base": "https://modaic-ai--grpo-demo-serve.modal.run/v1"
+    }
+  },
+  "metadata": {
+    "dependency_versions": {
+      "python": "3.13",
+      "dspy": "3.0.4",
+      "cloudpickle": "3.1"
+    }
+  }
+}