Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
 datasets:
 - abacusai/MetaMathFewshot
 - shahules786/orca-chat
 - anon8231489123/ShareGPT_Vicuna_unfiltered
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: Fewshot-Metamath-OrcaVicuna-Mistral
+  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: 59.64
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
+      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: 81.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
+      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: 61.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
+      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: 53.23
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
+      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=abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
+      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: 69.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abacusai/Fewshot-Metamath-OrcaVicuna-Mistral
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png)
@@ -53,4 +156,17 @@ Instruction tuned with the following parameters:
 
 # Bias, Risks, and Limitations
 
-The model has not been evaluated for safety and is only intended for research and experiments.
+The model has not been evaluated for safety and is only intended for research and experiments.
+# [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_abacusai__Fewshot-Metamath-OrcaVicuna-Mistral)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.33|
+|AI2 Reasoning Challenge (25-Shot)|59.64|
+|HellaSwag (10-Shot)              |81.82|
+|MMLU (5-Shot)                    |61.69|
+|TruthfulQA (0-shot)              |53.23|
+|Winogrande (5-shot)              |78.45|
+|GSM8k (5-shot)                   |69.14|
+