Adding Evaluation Results

README.md

@@ -2,6 +2,109 @@
 license: apache-2.0
 tags:
 - merge
+model-index:
+- name: MetaMath-Tulpar-7b-v2-Slerp
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 65.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-Tulpar-7b-v2-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 85.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-Tulpar-7b-v2-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-Tulpar-7b-v2-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 56.5
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-Tulpar-7b-v2-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 79.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-Tulpar-7b-v2-Slerp
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-Tulpar-7b-v2-Slerp
+      name: Open LLM Leaderboard
 ---
 # MetaMath-Tulpar-7b-v2-Slerp
 
@@ -28,4 +131,17 @@ parameters:
     - value: 0.5 # fallback for rest of tensors
 dtype: float16
 
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PulsarAI__MetaMath-Tulpar-7b-v2-Slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.20|
+|AI2 Reasoning Challenge (25-Shot)|65.61|
+|HellaSwag (10-Shot)              |85.16|
+|MMLU (5-Shot)                    |63.49|
+|TruthfulQA (0-shot)              |56.50|
+|Winogrande (5-shot)              |79.48|
+|GSM8k (5-shot)                   |70.96|
+