Adding Evaluation Results (#1)

- Adding Evaluation Results (8d65fefd7fa8373c0848d1e6980c7b6e3c77bef0)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,21 +1,124 @@
 ---
+language:
+- en
 license: cc-by-nc-nd-4.0
+library_name: transformers
 tags:
 - moe
 - merge
 - medical
 - mergekit
-base_model:
-- sethuiyer/Dr_Samantha_7b_mistral
-- fblgit/UNA-TheBeagle-7b-v1
-language:
-- en
 datasets:
 - medmcqa
 - cognitivecomputations/samantha-data
 - jondurbin/bagel-v0.3
-library_name: transformers
+base_model:
+- sethuiyer/Dr_Samantha_7b_mistral
+- fblgit/UNA-TheBeagle-7b-v1
 pipeline_tag: text-generation
+model-index:
+- name: MedleyMD
+  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: 66.47
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/MedleyMD
+      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: 86.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/MedleyMD
+      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: 65.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/MedleyMD
+      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: 52.46
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/MedleyMD
+      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: 80.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/MedleyMD
+      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: 68.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/MedleyMD
+      name: Open LLM Leaderboard
 ---
 
 # MedleyMD
@@ -114,4 +217,17 @@ It is composed of a topmost gating network that assigns weights to each expert n
 The expert networks are trained independently, and the gating network learns to choose the best combination of these experts to make the final prediction.
 Mixout demonstrates a stronger ability to handle complex data distributions and is more efficient in terms of training time and memory usage compared to a
 traditional ensemble approach.
-```
+```
+# [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_sethuiyer__MedleyMD)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.89|
+|AI2 Reasoning Challenge (25-Shot)|66.47|
+|HellaSwag (10-Shot)              |86.06|
+|MMLU (5-Shot)                    |65.10|
+|TruthfulQA (0-shot)              |52.46|
+|Winogrande (5-shot)              |80.27|
+|GSM8k (5-shot)                   |68.99|
+