Adding Evaluation Results

README.md

@@ -1,5 +1,108 @@
 ---
 license: cc-by-nc-4.0
+model-index:
+- name: Psyfighter2-Noromaid-ties-Capybara-13B
+  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: 62.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B
+      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: 83.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B
+      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: 56.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B
+      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: 51.44
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B
+      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: 77.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B
+      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: 30.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B
+      name: Open LLM Leaderboard
 ---
 
 Just for experimental purposes, not stable.
@@ -14,4 +117,17 @@ Finetuned on dataset [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capy
 | MMLU (5-shot) | 56.59 |
 | TruthfulQA (0-shot) | 51.44 |
 | Winogrande (5-shot) | 77.03 |
-| GSM8K (5-shot) | 30.4 |
+| GSM8K (5-shot) | 30.4 |
+# [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_diffnamehard__Psyfighter2-Noromaid-ties-Capybara-13B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |60.27|
+|AI2 Reasoning Challenge (25-Shot)|62.29|
+|HellaSwag (10-Shot)              |83.87|
+|MMLU (5-Shot)                    |56.59|
+|TruthfulQA (0-shot)              |51.44|
+|Winogrande (5-shot)              |77.03|
+|GSM8k (5-shot)                   |30.40|
+