Adding Evaluation Results

README.md

@@ -1,8 +1,4 @@
 ---
-license: apache-2.0
-datasets:
-- Open-Orca/OpenOrca
-- OpenAssistant/oasst_top1_2023-08-25
 language:
 - bg
 - ca
@@ -24,8 +20,114 @@ language:
 - sr
 - sv
 - uk
-
+license: apache-2.0
 library_name: transformers
+datasets:
+- Open-Orca/OpenOrca
+- OpenAssistant/oasst_top1_2023-08-25
+model-index:
+- name: Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+  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: 60.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+      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: 82.07
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+      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: 62.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+      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: 46.38
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+      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: 78.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+      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: 40.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
+      name: Open LLM Leaderboard
 ---
 
 
@@ -161,3 +263,17 @@ outputs = model.generate(generation_config=generation_config,
                                 input_ids=inputs,)
 tokenizer.decode(outputs[0], skip_special_tokens=False) #True
 ```
+
+# [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_NickyNicky__Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.65|
+|AI2 Reasoning Challenge (25-Shot)|60.49|
+|HellaSwag (10-Shot)              |82.07|
+|MMLU (5-Shot)                    |62.34|
+|TruthfulQA (0-shot)              |46.38|
+|Winogrande (5-shot)              |78.45|
+|GSM8k (5-shot)                   |40.18|
+