Adding Evaluation Results (#3)

- Adding Evaluation Results (bbae4a8440862e890c1947970d52fcf35a592aef)

README.md

@@ -16,8 +16,7 @@ model-index:
       value: 48.13
       name: strict accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -32,8 +31,7 @@ model-index:
       value: 5.19
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -48,8 +46,7 @@ model-index:
       value: 1.36
       name: exact match
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -64,8 +61,7 @@ model-index:
       value: 2.35
       name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -80,8 +76,7 @@ model-index:
       value: 4.05
       name: acc_norm
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -98,8 +93,7 @@ model-index:
       value: 3.05
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
       name: Open LLM Leaderboard
 ---
 
@@ -297,3 +291,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ## Model Card Contact
 [email protected]
 
+
+# [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_DeepAutoAI__Explore_Llama-3.2-1B-Inst_v1.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |14.12|
+|IFEval (0-Shot)    |58.44|
+|BBH (3-Shot)       | 8.82|
+|MATH Lvl 5 (4-Shot)| 6.04|
+|GPQA (0-shot)      | 1.68|
+|MuSR (0-shot)      | 0.66|
+|MMLU-PRO (5-shot)  | 9.09|
+