初始化项目，由ModelHub XC社区提供模型

Model: GitMarco27/zagreus-0.4b-italic-kl
Source: Original Platform

evaluation/config.yaml

@@ -0,0 +1,22 @@
+provider: custom_openai
+model: zagreus-0.4b-italic-kl
+api_key: EMPTY
+temperature: 0.0
+max_tokens: 350
+system_message: null
+provider_kwargs:
+  base_url: http://127.0.0.1:8000/v1
+rate_limiting:
+  enabled: false
+  requests_per_minute: 15
+limit: null
+fast: true
+data:
+  data_file: ./italic.jsonl
+  few_shot_file: null
+  output_dir: results
+num_threads: 30
+auto_resume: true
+checkpointing:
+  enabled: true
+  checkpoint_interval: 50

evaluation/domain_dev.json

@@ -0,0 +1,42 @@
+{
+  "schema": 1,
+  "model": "zagreus-0.4b-italic-kl",
+  "data": "domain_pool_dev.jsonl",
+  "n": 480,
+  "shots": 0,
+  "seed": 42,
+  "accuracy": 0.58125,
+  "prediction_distribution": {
+    "B": 139,
+    "C": 92,
+    "A": 147,
+    "D": 102
+  },
+  "gold_distribution": {
+    "A": 120,
+    "C": 132,
+    "B": 120,
+    "D": 108
+  },
+  "per_category": {
+    "lexicon": {
+      "accuracy": 0.85,
+      "n": 120
+    },
+    "synonyms_and_antonyms": {
+      "accuracy": 0.8083333333333333,
+      "n": 120
+    },
+    "culture": {
+      "accuracy": 0.375,
+      "n": 120
+    },
+    "civic_education": {
+      "accuracy": 0.2916666666666667,
+      "n": 120
+    }
+  },
+  "empty_predictions": 0,
+  "invalid_predictions": 0,
+  "wall_seconds": 18.380833387374878
+}

evaluation/official_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cecd85d6577725611a6ce7cef873fabe41028a66a12276e99238646892f383
+size 18695104

evaluation/provenance.json

@@ -0,0 +1,43 @@
+{
+  "schema": 1,
+  "model": "zagreus-0.4b-italic-kl",
+  "model_weights_sha256": "5e0284467f727f22000b897a3c40f3e5c24b519de463f71a4212149fe1913c6e",
+  "base_model": "mii-llm/zagreus-0.4B-ita",
+  "base_revision": "f463a5beabf054809ee3cc702c711215a5fde690",
+  "evaluator": "Crisp-Unimib/ITALIC",
+  "evaluator_revision": "92df420ff686babeea54e217b9f90f8471374916",
+  "evaluator_sha256": "ed4e4c63109245146040b234018ffb720ed088e6d55aef074cd9755dc3ed94f1",
+  "italic_data_sha256": "ca877846f19a6d781ba151382e4f43b10efad1a7e375b5e0c50b047a3917e0af",
+  "original_official_results_sha256": "eb5d61796c868d583c8b37794589ce1ac24984a08ccae896ee96d3996889c0b0",
+  "public_official_results_sha256": "a8cecd85d6577725611a6ce7cef873fabe41028a66a12276e99238646892f383",
+  "public_result_transformations": [
+    "Changed only the local served-model alias to zagreus-0.4b-italic-kl."
+  ],
+  "evaluation": {
+    "questions": 10000,
+    "zero_shot": true,
+    "fast": true,
+    "temperature": 0.0,
+    "metrics": {
+      "accuracy": 0.3381,
+      "accuracy:std": 0.4730627759610768
+    },
+    "prediction_counts": {
+      "A": 3780,
+      "B": 2611,
+      "C": 2400,
+      "D": 1209
+    },
+    "empty_parses": 0,
+    "started_at": "2026-07-15T07:38:58Z",
+    "ended_at": "2026-07-15T07:46:32Z",
+    "wall_seconds": 454
+  },
+  "final_run": {
+    "hardware": "NVIDIA A100 80GB PCIe",
+    "resource_wall_hours": 0.7531477777777777,
+    "h100_equivalent_hours": 0.3622406266820453,
+    "estimated_provider_cost_usd": 1.046875411111111,
+    "within_10_h100_equivalent_hours": true
+  }
+}