Adding Evaluation Results (#3)

- Adding Evaluation Results (6629d56f99e9f7f828cd674802276b399a4d9507)


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

README.md

@@ -1,9 +1,112 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - Open-Orca/OpenOrca
-language:
-- en
+model-index:
+- name: Mistral-7B-attention-100000
+  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: 52.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/Mistral-7B-attention-100000
+      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: 78.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/Mistral-7B-attention-100000
+      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: 54.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/Mistral-7B-attention-100000
+      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: 45.37
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/Mistral-7B-attention-100000
+      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: 75.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/Mistral-7B-attention-100000
+      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: 16.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/Mistral-7B-attention-100000
+      name: Open LLM Leaderboard
 ---
 
 # Model Details
@@ -27,4 +130,17 @@ We random sample Open-Orca dataset. (We finetune the 100,000 dataset)
 https://github.com/trailerAI
 
 # License
-Apache License 2.0
+Apache License 2.0
+# [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_NLUHOPOE__Mistral-7B-attention-100000)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |54.05|
+|AI2 Reasoning Challenge (25-Shot)|52.99|
+|HellaSwag (10-Shot)              |78.54|
+|MMLU (5-Shot)                    |54.79|
+|TruthfulQA (0-shot)              |45.37|
+|Winogrande (5-shot)              |75.61|
+|GSM8k (5-shot)                   |16.98|
+