server-inference push writingprompts_quality

program.json

@@ -0,0 +1,44 @@
+{
+  "traces": [],
+  "train": [],
+  "demos": [],
+  "signature": {
+    "instructions": "Rate the quality of a story written in response to a creative writing prompt.\n\nEvaluate across four dimensions:\n- Adherence: Does the story genuinely respond to the prompt, or does it ignore it?\n- Creativity: Is the story imaginative, surprising, or does it offer a fresh angle?\n- Craft: Is the prose well-written \u2014 pacing, voice, structure?\n- Engagement: Would a reader want to finish the story?\n\nScore 1 = poor (off-topic, clich\u00e9d, or unreadable), 3 = adequate (responds\nto prompt but unremarkable), 5 = excellent (engaging, creative, well-crafted).\n\nNote: you may only see the first portion of longer stories.  Judge based on\nwhat is available.\n\nAs you reason, note any uncertainties, ambiguities, and gaps \u2014 both in how\nthe instructions apply to the task at hand and in whether you have the\nknowledge needed to solve it. Be honest in your reasoning when you are\nunsure about your answer.",
+    "fields": [
+      {
+        "prefix": "Prompt:",
+        "description": "The creative writing prompt."
+      },
+      {
+        "prefix": "Story:",
+        "description": "The story written in response to the prompt (may be truncated)."
+      },
+      {
+        "prefix": "Reasoning:",
+        "description": "Step-by-step reasoning, including uncertainty when relevant."
+      },
+      {
+        "prefix": "Quality Score:",
+        "description": "Overall story quality score on a 1-5 scale."
+      }
+    ]
+  },
+  "lm": {
+    "model": "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo",
+    "model_type": "chat",
+    "cache": true,
+    "num_retries": 3,
+    "finetuning_model": null,
+    "launch_kwargs": {},
+    "train_kwargs": {},
+    "temperature": null,
+    "max_tokens": null
+  },
+  "metadata": {
+    "dependency_versions": {
+      "python": "3.11",
+      "dspy": "3.1.3",
+      "cloudpickle": "3.1"
+    }
+  }
+}