Adding Evaluation Results

README.md

@@ -1,20 +1,115 @@
 ---
-base_model: unsloth/phi-4-unsloth-bnb-4bit
+language:
+- en
+license: apache-2.0
 tags:
 - text-generation-inference
 - transformers
 - unsloth
 - llama
 - gguf
-license: apache-2.0
-language:
-- en
+base_model: unsloth/phi-4-unsloth-bnb-4bit
 datasets:
 - bespokelabs/Bespoke-Stratos-17k
 - bespokelabs/Bespoke-Stratos-35k
 - NovaSky-AI/Sky-T1_data_17k
 - Quazim0t0/BenfordsLawReasoningJSON
 - open-thoughts/OpenThoughts-114k
+model-index:
+- name: Phi4.Turn.R1Distill_v1.5.1-Tensors
+  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: 29.95
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
+      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: 49.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
+      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: 1.59
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
+      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: 2.46
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
+      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: 7.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
+      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: 45.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
+      name: Open LLM Leaderboard
 ---
 
 # TurnPhi Project
@@ -97,4 +192,17 @@ tokenizer = AutoTokenizer.from_pretrained(base_model)
 model = AutoModelForCausalLM.from_pretrained(base_model)
 model = PeftModel.from_pretrained(model, lora_adapter)
 
-model.eval()
+model.eval()
+# [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/Quazim0t0__Phi4.Turn.R1Distill_v1.5.1-Tensors-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.67|
+|IFEval (0-Shot)    |29.95|
+|BBH (3-Shot)       |49.22|
+|MATH Lvl 5 (4-Shot)| 1.59|
+|GPQA (0-shot)      | 2.46|
+|MuSR (0-shot)      | 7.04|
+|MMLU-PRO (5-shot)  |45.75|
+