Adding Evaluation Results (#4)

- Adding Evaluation Results (2da0f0b568794e2e089294ee521c3c62ec4924ba)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,7 +1,110 @@
 ---
-license: llama2
 language:
 - en
+license: llama2
+model-index:
+- name: Midnight-Rose-70B-v2.0.3
+  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: 70.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Midnight-Rose-70B-v2.0.3
+      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: 87.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Midnight-Rose-70B-v2.0.3
+      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: 69.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Midnight-Rose-70B-v2.0.3
+      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: 65.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Midnight-Rose-70B-v2.0.3
+      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: 81.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Midnight-Rose-70B-v2.0.3
+      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: 28.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Midnight-Rose-70B-v2.0.3
+      name: Open LLM Leaderboard
 ---
 <div style="width: auto; margin-left: auto; margin-right: auto">
 <img src="https://i.imgur.com/X3SBrIb.png" alt="MidnightRose" style="width: 100%; min-width: 400px; display: block; margin: auto;">
@@ -250,4 +353,17 @@ parameters:
   t:
     - value: [0.4, 0.6, 0.5]
 dtype: float16
-```
+```
+# [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_sophosympatheia__Midnight-Rose-70B-v2.0.3)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.11|
+|AI2 Reasoning Challenge (25-Shot)|70.65|
+|HellaSwag (10-Shot)              |87.50|
+|MMLU (5-Shot)                    |69.64|
+|TruthfulQA (0-shot)              |65.27|
+|Winogrande (5-shot)              |81.22|
+|GSM8k (5-shot)                   |28.35|
+