Adding Evaluation Results (#4)

- Adding Evaluation Results (842a85493025972dd3883e334c466859d2a8a8fc)

README.md

@@ -13,7 +13,12 @@ tags:
 - tool-use
 base_model:
 - Qwen/Qwen2.5-14B-Instruct
+datasets:
+- nvidia/HelpSteer2
+- google/Synthetic-Persona-Chat
+- mlabonne/orpo-dpo-mix-40k
 pipeline_tag: text-generation
+new_version: sthenno-com/miscii-14b-1225
 model-index:
 - name: miscii-14b-1028
   results:
@@ -30,8 +35,7 @@ model-index:
       value: 82.37
       name: strict accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -46,8 +50,7 @@ model-index:
       value: 49.26
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -62,8 +65,7 @@ model-index:
       value: 6.34
       name: exact match
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -78,8 +80,7 @@ model-index:
       value: 14.21
       name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -94,8 +95,7 @@ model-index:
       value: 12
       name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -112,14 +112,8 @@ model-index:
       value: 46.14
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
       name: Open LLM Leaderboard
-datasets:
-- nvidia/HelpSteer2
-- google/Synthetic-Persona-Chat
-- mlabonne/orpo-dpo-mix-40k
-new_version: sthenno-com/miscii-14b-1225
 ---
 
 # miscii-14b-1028
@@ -167,4 +161,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MuSR (0-shot)      |12.00|
 |MMLU-PRO (5-shot)  |46.14|
 
-$$\large{\text{There's nothing more to Show}}$$
+$$\large{\text{There's nothing more to Show}}$$
+# [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/sthenno-com__miscii-14b-1028-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |42.38|
+|IFEval (0-Shot)    |82.37|
+|BBH (3-Shot)       |49.26|
+|MATH Lvl 5 (4-Shot)|50.30|
+|GPQA (0-shot)      |14.21|
+|MuSR (0-shot)      |12.00|
+|MMLU-PRO (5-shot)  |46.14|
+