Adding Evaluation Results (#3)

- Adding Evaluation Results (5ae7316b931c7e40d1cc2eb43872c234dd69ccde)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,6 +1,8 @@
 ---
 license: apache-2.0
 library_name: transformers
+datasets:
+- vicgalle/configurable-system-prompt-multitask
 model-index:
 - name: Configurable-Yi-1.5-9B-Chat
   results:
@@ -19,8 +21,7 @@ model-index:
       value: 64.16
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -36,8 +37,7 @@ model-index:
       value: 81.7
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -54,8 +54,7 @@ model-index:
       value: 70.99
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -71,8 +70,7 @@ model-index:
     - type: mc2
       value: 58.75
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -89,8 +87,7 @@ model-index:
       value: 76.8
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -107,11 +104,100 @@ model-index:
       value: 70.58
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
+      name: Open LLM Leaderboard
+  - 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: 43.23
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-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: 35.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-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: 6.12
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-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: 12.42
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-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: 12.02
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-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: 33.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat
       name: Open LLM Leaderboard
-datasets:
-- vicgalle/configurable-system-prompt-multitask
 ---
 
 
@@ -217,4 +303,17 @@ If you find this work, data and/or models useful for your research, please consi
       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_vicgalle__Configurable-Yi-1.5-9B-Chat)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.77|
+|IFEval (0-Shot)    |43.23|
+|BBH (3-Shot)       |35.33|
+|MATH Lvl 5 (4-Shot)| 6.12|
+|GPQA (0-shot)      |12.42|
+|MuSR (0-shot)      |12.02|
+|MMLU-PRO (5-shot)  |33.50|
+