Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: apache-2.0
+model-index:
+- name: TinyLlama-1.1B-Chat-v1.0-x2-MoE
+  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: 36.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
+      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: 61.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
+      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: 24.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
+      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: 37.37
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
+      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: 60.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
+      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: 2.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE
+      name: Open LLM Leaderboard
 ---
 Testing model.
 
@@ -13,4 +116,17 @@ experts:
     positive_prompts: [""]
   - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
     positive_prompts: [""]
-```
+```
+# [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_AIChenKai__TinyLlama-1.1B-Chat-v1.0-x2-MoE)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.98|
+|AI2 Reasoning Challenge (25-Shot)|36.01|
+|HellaSwag (10-Shot)              |61.04|
+|MMLU (5-Shot)                    |24.81|
+|TruthfulQA (0-shot)              |37.37|
+|Winogrande (5-shot)              |60.38|
+|GSM8k (5-shot)                   | 2.27|
+