Adding Evaluation Results

README.md

@@ -1,17 +1,112 @@
 ---
-license: llama3.1
 language:
 - en
-inference: false
-fine-tuning: false
+license: llama3.1
+library_name: transformers
 tags:
 - nvidia
 - llama3.1
+base_model: meta-llama/Llama-3.1-70B-Instruct
 datasets:
 - nvidia/HelpSteer2
-base_model: meta-llama/Llama-3.1-70B-Instruct
+inference: false
+fine-tuning: false
 pipeline_tag: text-generation
-library_name: transformers
+model-index:
+- name: Llama-3.1-Nemotron-70B-Instruct-HF
+  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: 73.81
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+      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: 47.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+      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: 26.96
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+      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: 1.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+      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: 13.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+      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: 43.54
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+      name: Open LLM Leaderboard
 ---
 # Model Overview
 
@@ -178,4 +273,17 @@ If you find this model useful, please cite the following works
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2410.01257}, 
 }
-```
+```
+# [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_nvidia__Llama-3.1-Nemotron-70B-Instruct-HF)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |34.29|
+|IFEval (0-Shot)    |73.81|
+|BBH (3-Shot)       |47.11|
+|MATH Lvl 5 (4-Shot)|26.96|
+|GPQA (0-shot)      | 1.12|
+|MuSR (0-shot)      |13.20|
+|MMLU-PRO (5-shot)  |43.54|
+