Adding Evaluation Results

README.md

@@ -1,17 +1,112 @@
 ---
-license: mit
-datasets:
-- ServiceNow-AI/R1-Distill-SFT
 language:
 - en
-base_model:
-- meta-llama/Llama-3.2-3B-Instruct
-pipeline_tag: text-generation
+license: mit
 library_name: transformers
 tags:
 - reasoning
 - axolotl
 - r1
+base_model:
+- meta-llama/Llama-3.2-3B-Instruct
+datasets:
+- ServiceNow-AI/R1-Distill-SFT
+pipeline_tag: text-generation
+model-index:
+- name: DeepSeek-R1-Distill-Llama-3B
+  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: 70.93
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      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: 21.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      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: 20.92
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      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: 1.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      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: 2.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      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: 21.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/DeepSeek-R1-Distill-Llama-3B
+      name: Open LLM Leaderboard
 ---
 
 # DeepSeek-R1-Distill-Llama-3B
@@ -190,4 +285,17 @@ Always use <think> </think> tags even if they are not necessary.
 
 # Support
 
-<a href="https://www.buymeacoffee.com/suayptalha" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
+<a href="https://www.buymeacoffee.com/suayptalha" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
+# [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/suayptalha__DeepSeek-R1-Distill-Llama-3B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.27|
+|IFEval (0-Shot)    |70.93|
+|BBH (3-Shot)       |21.45|
+|MATH Lvl 5 (4-Shot)|20.92|
+|GPQA (0-shot)      | 1.45|
+|MuSR (0-shot)      | 2.91|
+|MMLU-PRO (5-shot)  |21.98|
+