Adding Evaluation Results (#1)

- Adding Evaluation Results (6c17493afdcfeb06b7bb604e24434d16ff53b6b0)


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

README.md

@@ -1,16 +1,111 @@
 ---
-license: apache-2.0
-library_name: transformers
 language:
 - en
 - zh
-pipeline_tag: text-generation
-base_model:
-- Qwen/Qwen2.5-14B-Instruct
+license: apache-2.0
+library_name: transformers
 tags:
 - chat
 - conversational
 - custom-research
+base_model:
+- Qwen/Qwen2.5-14B-Instruct
+pipeline_tag: text-generation
+model-index:
+- name: miscii-14b-1028
+  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: 82.37
+      name: strict accuracy
+    source:
+      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
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 49.26
+      name: normalized accuracy
+    source:
+      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
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 6.34
+      name: exact match
+    source:
+      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
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 14.21
+      name: acc_norm
+    source:
+      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
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 12.0
+      name: acc_norm
+    source:
+      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
+      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: 46.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
+      name: Open LLM Leaderboard
 ---
 
 # miscii-14b-1028
@@ -24,3 +119,17 @@ See [Report for miscii-1020](https://api.wandb.ai/links/flandrelabs-carnegie-mel
 
 $$\large{\text{There's nothing more to Show}}$$
 
+
+# [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/details_sthenno-com__miscii-14b-1028)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |35.05|
+|IFEval (0-Shot)    |82.37|
+|BBH (3-Shot)       |49.26|
+|MATH Lvl 5 (4-Shot)| 6.34|
+|GPQA (0-shot)      |14.21|
+|MuSR (0-shot)      |12.00|
+|MMLU-PRO (5-shot)  |46.14|
+