Adding Evaluation Results (#23)

- Adding Evaluation Results (7ca07b95ff1fac8f691a73fc2811ebbd97ca01ad)


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

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 model-index:
 - name: miqu-1-70b-sf
   results:
@@ -17,8 +19,7 @@ model-index:
       value: 73.04
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -34,8 +35,7 @@ model-index:
       value: 88.61
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -52,8 +52,7 @@ model-index:
       value: 75.49
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -69,8 +68,7 @@ model-index:
     - type: mc2
       value: 69.38
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -87,8 +85,7 @@ model-index:
       value: 85.32
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -105,11 +102,100 @@ model-index:
       value: 67.7
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      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: 51.82
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      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: 43.81
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      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: 10.8
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      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: 13.42
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      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: 17.21
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
+      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: 35.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=152334H/miqu-1-70b-sf
       name: Open LLM Leaderboard
-language:
-- en
 ---
 
 update: added NOMERGE license
@@ -290,3 +376,17 @@ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
 ```
+
+# [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_152334H__miqu-1-70b-sf)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.82|
+|IFEval (0-Shot)    |51.82|
+|BBH (3-Shot)       |43.81|
+|MATH Lvl 5 (4-Shot)|10.80|
+|GPQA (0-shot)      |13.42|
+|MuSR (0-shot)      |17.21|
+|MMLU-PRO (5-shot)  |35.87|
+