Adding Evaluation Results (#1)

- Adding Evaluation Results (e2dd0d351f6511677465e977b26251a514ba11da)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,11 +1,114 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 library_name: transformers
-pipeline_tag: text-generation
 datasets:
 - monology/VMware-open-instruct-higgsfield
+pipeline_tag: text-generation
+model-index:
+- name: openinstruct-mistral-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: 59.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-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: 82.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-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: 60.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-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: 48.76
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-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: 79.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-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: 50.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=monology/openinstruct-mistral-7b
+      name: Open LLM Leaderboard
 ---
 
 # OpenInstruct Mistral-7B
@@ -32,4 +135,17 @@ Below is an instruction that describes a task. Write a response that appropriate
 - top_p 0.95
 - repetition_penalty: 1.1
 
-\*as of 21 Nov 2023. "commercially-usable" includes both an open-source base model and a *non-synthetic* open-source finetune dataset. updated leaderboard results available [here](https://huggingfaceh4-open-llm-leaderboard.hf.space).
+\*as of 21 Nov 2023. "commercially-usable" includes both an open-source base model and a *non-synthetic* open-source finetune dataset. updated leaderboard results available [here](https://huggingfaceh4-open-llm-leaderboard.hf.space).
+# [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_monology__openinstruct-mistral-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.64|
+|AI2 Reasoning Challenge (25-Shot)|59.73|
+|HellaSwag (10-Shot)              |82.77|
+|MMLU (5-Shot)                    |60.55|
+|TruthfulQA (0-shot)              |48.76|
+|Winogrande (5-shot)              |79.56|
+|GSM8k (5-shot)                   |50.49|
+