Adding Evaluation Results

README.md

@@ -1,13 +1,107 @@
 ---
+license: other
 library_name: transformers
 base_model: nvidia/Mistral-NeMo-Minitron-8B-Base
 datasets:
 - teknium/OpenHermes-2.5
 pipeline_tag: text-generation
-license: other
 license_name: nvidia-open-model-license
-license_link: >-
-  https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
+license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
+model-index:
+- name: Mistral-NeMo-Minitron-8B-Chat
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 44.52
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rasyosef/Mistral-NeMo-Minitron-8B-Chat
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 26.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rasyosef/Mistral-NeMo-Minitron-8B-Chat
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.76
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rasyosef/Mistral-NeMo-Minitron-8B-Chat
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rasyosef/Mistral-NeMo-Minitron-8B-Chat
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 12.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rasyosef/Mistral-NeMo-Minitron-8B-Chat
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 15.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rasyosef/Mistral-NeMo-Minitron-8B-Chat
+      name: Open LLM Leaderboard
 ---
 
 # Mistral-NeMo-Minitron-8B-Chat
@@ -95,3 +189,17 @@ These benchmarks were run using EleutherAI's [lm-evaluation-harness](https://git
 Here's a colab notebook with a chat interface, you can use this to interact with the chat model.
 
 https://huggingface.co/rasyosef/Mistral-NeMo-Minitron-8B-Chat/blob/main/Mistral_NeMo_Minitron_8B_chatbot.ipynb
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rasyosef__Mistral-NeMo-Minitron-8B-Chat)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |17.22|
+|IFEval (0-Shot)    |44.52|
+|BBH (3-Shot)       |26.04|
+|MATH Lvl 5 (4-Shot)| 0.76|
+|GPQA (0-shot)      | 3.47|
+|MuSR (0-shot)      |12.94|
+|MMLU-PRO (5-shot)  |15.60|
+