Adding Evaluation Results (#2)

- Adding Evaluation Results (bbe538a3999bb58628b746ba1ed144720c488421)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 tags:
 - merge
 - mergekit
@@ -8,7 +9,101 @@ tags:
 base_model:
 - prometheus-eval/prometheus-8x7b-v2.0
 - mistralai/Mixtral-8x7B-Instruct-v0.1
-license: apache-2.0
+model-index:
+- name: Merge-Mixtral-Prometheus-8x7B
+  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: 57.44
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Merge-Mixtral-Prometheus-8x7B
+      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: 34.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Merge-Mixtral-Prometheus-8x7B
+      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: 8.31
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Merge-Mixtral-Prometheus-8x7B
+      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: 7.83
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Merge-Mixtral-Prometheus-8x7B
+      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: 9.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Merge-Mixtral-Prometheus-8x7B
+      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: 29.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Merge-Mixtral-Prometheus-8x7B
+      name: Open LLM Leaderboard
 ---
 
 # Merge-Mixtral-Prometheus-8x7B 
@@ -58,4 +153,17 @@ print(outputs[0]["generated_text"])
 
 ## Paper citation
 
-Paper: https://arxiv.org/abs/2406.07188
+Paper: https://arxiv.org/abs/2406.07188
+# [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_vicgalle__Merge-Mixtral-Prometheus-8x7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.61|
+|IFEval (0-Shot)    |57.44|
+|BBH (3-Shot)       |34.65|
+|MATH Lvl 5 (4-Shot)| 8.31|
+|GPQA (0-shot)      | 7.83|
+|MuSR (0-shot)      | 9.59|
+|MMLU-PRO (5-shot)  |29.82|
+