Adding Evaluation Results

README.md

@@ -1,14 +1,109 @@
 ---
-base_model:
-- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
-- cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
+license: apache-2.0
 tags:
 - merge
 - mergekit
 - lazymergekit
 - Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
 - cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
-license: apache-2.0
+base_model:
+- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+- cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
+model-index:
+- name: MistralPhi3-11B
+  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: 19.43
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/MistralPhi3-11B
+      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: 46.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/MistralPhi3-11B
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/MistralPhi3-11B
+      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: 10.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/MistralPhi3-11B
+      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: 12.23
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/MistralPhi3-11B
+      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: 40.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/MistralPhi3-11B
+      name: Open LLM Leaderboard
 ---
 
 # MistralPhi3-14B-slerp
@@ -61,4 +156,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_allknowingroger__MistralPhi3-11B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.63|
+|IFEval (0-Shot)    |19.43|
+|BBH (3-Shot)       |46.16|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      |10.96|
+|MuSR (0-shot)      |12.23|
+|MMLU-PRO (5-shot)  |40.97|
+