Adding Evaluation Results (#1)

- Adding Evaluation Results (24d2fdd231d753334cbee3062db952b09a9921fe)

README.md

@@ -1,4 +1,8 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
 tags:
 - merge
 - mergekit
@@ -9,10 +13,109 @@ tags:
 base_model:
 - ResplendentAI/Datura_7B
 - Epiculous/Mika-7B
-language:
-- en
-library_name: transformers
-license: apache-2.0
+model-index:
+- name: Foxglove_7B
+  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: 67.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aridoverrun/Foxglove_7B
+      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: 86.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aridoverrun/Foxglove_7B
+      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: 62.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aridoverrun/Foxglove_7B
+      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: 69.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aridoverrun/Foxglove_7B
+      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: 80.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aridoverrun/Foxglove_7B
+      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: 44.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aridoverrun/Foxglove_7B
+      name: Open LLM Leaderboard
 ---
 <div style="margin-bottom: -40px; margin-top: -30px;">
     <img src="https://cdn-uploads.huggingface.co/production/uploads/65ad2502043d53781aad2ee4/ZrffOEBz2rxwAwdgzOkhd.png" alt="favicon" style="display: inline-block; vertical-align: middle; width: 25px; height: 25px; margin-right: 10px;">
@@ -70,4 +173,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_aridoverrun__Foxglove_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.77|
+|AI2 Reasoning Challenge (25-Shot)|67.83|
+|HellaSwag (10-Shot)              |86.57|
+|MMLU (5-Shot)                    |62.89|
+|TruthfulQA (0-shot)              |69.64|
+|Winogrande (5-shot)              |80.74|
+|GSM8k (5-shot)                   |44.96|
+