Adding Evaluation Results

README.md

@@ -1,7 +1,102 @@
 ---
-license: other
 language:
 - en
+license: other
+model-index:
+- name: Hathor_Stable-v0.2-L3-8B
+  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: 71.75
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nitral-AI/Hathor_Stable-v0.2-L3-8B
+      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: 32.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nitral-AI/Hathor_Stable-v0.2-L3-8B
+      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: 9.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nitral-AI/Hathor_Stable-v0.2-L3-8B
+      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: 4.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nitral-AI/Hathor_Stable-v0.2-L3-8B
+      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: 5.56
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nitral-AI/Hathor_Stable-v0.2-L3-8B
+      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: 29.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nitral-AI/Hathor_Stable-v0.2-L3-8B
+      name: Open LLM Leaderboard
 ---
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/kJF-ER-uPDH6O2m6qB9wg.jpeg)
 
@@ -12,3 +107,17 @@ language:
 # Quants From Bartowski <3: https://huggingface.co/bartowski/Hathor-L3-8B-v.02-GGUF https://huggingface.co/bartowski/Hathor-L3-8B-v.02-exl2
 ---
 # Notes: Hathor is trained on 3 epochs of private data, synthetic opus instructons, a mix of light/classical novel data, roleplaying chat pairs over llama 3 8B instruct. (expanded)
+
+# [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_Nitral-AI__Hathor_Stable-v0.2-L3-8B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.70|
+|IFEval (0-Shot)    |71.75|
+|BBH (3-Shot)       |32.83|
+|MATH Lvl 5 (4-Shot)| 9.21|
+|GPQA (0-shot)      | 4.92|
+|MuSR (0-shot)      | 5.56|
+|MMLU-PRO (5-shot)  |29.96|
+