Adding Evaluation Results

README.md

@@ -1,11 +1,7 @@
 ---
-license: apache-2.0
 language:
 - en
-metrics:
-- accuracy
-- bertscore
-- bleu
+license: apache-2.0
 tags:
 - slm
 - llama
@@ -14,6 +10,113 @@ tags:
 datasets:
 - HuggingFaceH4/ultrachat_200k
 - HuggingFaceH4/ultrafeedback_binarized
+metrics:
+- accuracy
+- bertscore
+- bleu
+model-index:
+- name: zyte-1.1b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 37.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aihub-app/zyte-1.1b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 60.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aihub-app/zyte-1.1b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 24.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aihub-app/zyte-1.1b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 39.46
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aihub-app/zyte-1.1b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 62.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aihub-app/zyte-1.1b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 1.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aihub-app/zyte-1.1b
+      name: Open LLM Leaderboard
 ---
 # Model Card for Model ID
 
@@ -56,4 +159,17 @@ Stay Connected with AI Hub:
 
 - [LinkedIn](https://www.linkedin.com/company/aihub-app/)
 - [Download AI Hub App](https://ai-hub.app.link/install)
-- Email: [hello@getaihub.app](mailto:hello@getaihub.app)
+- Email: [hello@getaihub.app](mailto:hello@getaihub.app)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_aihub-app__zyte-1.1b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.70|
+|AI2 Reasoning Challenge (25-Shot)|37.54|
+|HellaSwag (10-Shot)              |60.82|
+|MMLU (5-Shot)                    |24.57|
+|TruthfulQA (0-shot)              |39.46|
+|Winogrande (5-shot)              |62.04|
+|GSM8k (5-shot)                   | 1.74|
+