Adding Evaluation Results (#1)

- Adding Evaluation Results (c4a6c19a478241ca32a0040fb8ad3e65d2a9611b)

README.md

@@ -1,5 +1,108 @@
 ---
 license: apache-2.0
+model-index:
+- name: mera-mix-4x7B
+  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: 72.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=meraGPT/mera-mix-4x7B
+      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: 89.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=meraGPT/mera-mix-4x7B
+      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: 64.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=meraGPT/mera-mix-4x7B
+      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: 77.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=meraGPT/mera-mix-4x7B
+      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: 85.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=meraGPT/mera-mix-4x7B
+      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: 66.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=meraGPT/mera-mix-4x7B
+      name: Open LLM Leaderboard
 ---
 
 # Model mera-mix-4x7B
@@ -18,3 +121,17 @@ You can try the model with the [Mera Mixture Chat](https://huggingface.co/spaces
 |[mera-mix-4x7B](https://huggingface.co/meraGPT/mera-mix-4x7B)|72.01|    88.82|63.67|     77.45|     84.61|71.65|  76.37|
 
 Raw eval results are available at this [gist](https://gist.github.com/codelion/78f88333230801c9bbaa6fc22078d820)
+
+# [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_meraGPT__mera-mix-4x7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.91|
+|AI2 Reasoning Challenge (25-Shot)|72.95|
+|HellaSwag (10-Shot)              |89.17|
+|MMLU (5-Shot)                    |64.44|
+|TruthfulQA (0-shot)              |77.17|
+|Winogrande (5-shot)              |85.64|
+|GSM8k (5-shot)                   |66.11|
+