Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
+license: apache-2.0
 datasets:
 - Mihaiii/OpenHermes-2.5-1k-longest-curated
-base_model: migtissera/Tess-10.7B-v1.5b
-inference: false
-license: apache-2.0
 metrics:
 - accuracy
+base_model: migtissera/Tess-10.7B-v1.5b
+inference: false
+model-index:
+- name: Bucharest-0.2
+  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: 64.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Bucharest-0.2
+      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: 84.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Bucharest-0.2
+      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: 66.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Bucharest-0.2
+      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: 45.3
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Bucharest-0.2
+      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: 83.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Bucharest-0.2
+      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: 56.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Bucharest-0.2
+      name: Open LLM Leaderboard
 ---
 
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
@@ -26,4 +129,17 @@ ASSISTANT:
 
 GGUF:
 
-[tsunemoto/Bucharest-0.2-GGUF](https://huggingface.co/tsunemoto/Bucharest-0.2-GGUF)
+[tsunemoto/Bucharest-0.2-GGUF](https://huggingface.co/tsunemoto/Bucharest-0.2-GGUF)
+# [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_Mihaiii__Bucharest-0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.81|
+|AI2 Reasoning Challenge (25-Shot)|64.59|
+|HellaSwag (10-Shot)              |84.87|
+|MMLU (5-Shot)                    |66.03|
+|TruthfulQA (0-shot)              |45.30|
+|Winogrande (5-shot)              |83.27|
+|GSM8k (5-shot)                   |56.79|
+