Adding Evaluation Results

README.md

@@ -1,17 +1,112 @@
 ---
-base_model:
-- chargoddard/prometheus-llama-3-8b-preference
-- chargoddard/prometheus-llama-3-8b-absolute
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- chargoddard/prometheus-llama-3-8b-preference
+- chargoddard/prometheus-llama-3-8b-absolute
 datasets:
 - prometheus-eval/Preference-Collection
 - prometheus-eval/Feedback-Collection
-language:
-- en
+model-index:
+- name: prometheus-2-llama-3-8b
+  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: 52.89
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chargoddard/prometheus-2-llama-3-8b
+      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: 27.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chargoddard/prometheus-2-llama-3-8b
+      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: 7.25
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chargoddard/prometheus-2-llama-3-8b
+      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: 3.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chargoddard/prometheus-2-llama-3-8b
+      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: 0.78
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chargoddard/prometheus-2-llama-3-8b
+      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: 23.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=chargoddard/prometheus-2-llama-3-8b
+      name: Open LLM Leaderboard
 ---
 # prometheus-2-llama-3-8b
 
@@ -52,4 +147,17 @@ Uses Llama 3 Instruct prompt format and the same prompts as prometheus-7b-v2.0.
     archivePrefix={arXiv},
     primaryClass={cs.CL}
 }
-```
+```
+# [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_chargoddard__prometheus-2-llama-3-8b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |19.16|
+|IFEval (0-Shot)    |52.89|
+|BBH (3-Shot)       |27.80|
+|MATH Lvl 5 (4-Shot)| 7.25|
+|GPQA (0-shot)      | 3.02|
+|MuSR (0-shot)      | 0.78|
+|MMLU-PRO (5-shot)  |23.19|
+