Adding Evaluation Results

README.md

@@ -11,6 +11,109 @@ datasets:
 base_model:
 - segmed/MedMistral-7B-v0.1
 - Guilherme34/Samantha-v2
+model-index:
+- name: Dr_Samantha_7b_mistral
+  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: 60.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 83.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 63.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 41.37
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 75.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 31.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      name: Open LLM Leaderboard
 ---
 
 # Dr_Samantha_7b_mistral
@@ -124,4 +227,17 @@ It's important to consult with a healthcare professional for a proper diagnosis
 ```
 
 ## GGUF Files
-GGUF files are available at [s3nh/sethuiyer-Dr_Samantha_7b_mistral-GGUF](https://huggingface.co/s3nh/sethuiyer-Dr_Samantha_7b_mistral-GGUF), thanks to [s3nh](https://huggingface.co/s3nh)
+GGUF files are available at [s3nh/sethuiyer-Dr_Samantha_7b_mistral-GGUF](https://huggingface.co/s3nh/sethuiyer-Dr_Samantha_7b_mistral-GGUF), thanks to [s3nh](https://huggingface.co/s3nh)
+# [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__Dr_Samantha_7b_mistral)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.25|
+|AI2 Reasoning Challenge (25-Shot)|60.41|
+|HellaSwag (10-Shot)              |83.65|
+|MMLU (5-Shot)                    |63.14|
+|TruthfulQA (0-shot)              |41.37|
+|Winogrande (5-shot)              |75.45|
+|GSM8k (5-shot)                   |31.46|
+