Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
-library_name: transformers
 license: apache-2.0
-datasets:
-- mlabonne/orpo-dpo-mix-40k
+library_name: transformers
 base_model:
 - microsoft/Phi-3-medium-4k-instruct
+datasets:
+- mlabonne/orpo-dpo-mix-40k
 pipeline_tag: text2text-generation
+model-index:
+- name: Neos-Phi-3-14B-v0.1
+  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: 40.22
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/Neos-Phi-3-14B-v0.1
+      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: 46.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/Neos-Phi-3-14B-v0.1
+      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: 16.69
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/Neos-Phi-3-14B-v0.1
+      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: 7.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/Neos-Phi-3-14B-v0.1
+      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: 10.53
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/Neos-Phi-3-14B-v0.1
+      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: 39.6
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/Neos-Phi-3-14B-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -23,3 +118,17 @@ pipeline_tag: text2text-generation
 ### Training Procedure
 
 Trained with ORPO trainer, and only first 5K rows are used for finetuning (5K out of 40K).
+
+# [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_BlackBeenie__Neos-Phi-3-14B-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.84|
+|IFEval (0-Shot)    |40.22|
+|BBH (3-Shot)       |46.63|
+|MATH Lvl 5 (4-Shot)|16.69|
+|GPQA (0-shot)      | 7.38|
+|MuSR (0-shot)      |10.53|
+|MMLU-PRO (5-shot)  |39.60|
+