Adding Evaluation Results

README.md

@@ -1,10 +1,14 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - LLMs
 - mistral
 - math
 - Intel
+datasets:
+- meta-math/MetaMathQA
 model-index:
 - name: neural-chat-7b-v3-2
   results:
@@ -12,11 +16,11 @@ model-index:
       type: Large Language Model
       name: Large Language Model
     dataset:
-      type: meta-math/MetaMathQA
       name: meta-math/MetaMathQA
+      type: meta-math/MetaMathQA
     metrics:
     - type: ARC (25-shot)
-      value: 67.49 
+      value: 67.49
       name: ARC (25-shot)
       verified: true
     - type: HellaSwag (10-shot)
@@ -39,10 +43,106 @@ model-index:
       value: 55.12
       name: GSM8K (5-shot)
       verified: true
-datasets:
-- meta-math/MetaMathQA
-language:
-- en
+  - 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: 67.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-2
+      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: 83.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-2
+      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: 63.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-2
+      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: 59.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-2
+      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: 79.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-2
+      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: 55.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Intel/neural-chat-7b-v3-2
+      name: Open LLM Leaderboard
 ---
 
 ## Model Details: Neural-Chat-v3-2
@@ -248,3 +348,17 @@ Here are a couple of useful links to learn more about Intel's AI software:
 ## Disclaimer
 
 The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
+
+# [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_Intel__neural-chat-7b-v3-2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.29|
+|AI2 Reasoning Challenge (25-Shot)|67.49|
+|HellaSwag (10-Shot)              |83.92|
+|MMLU (5-Shot)                    |63.55|
+|TruthfulQA (0-shot)              |59.68|
+|Winogrande (5-shot)              |79.95|
+|GSM8k (5-shot)                   |55.12|
+