Adding Evaluation Results (#4)

- Adding Evaluation Results (e8320f838f0e8a1667bbaeecd9d272bdf99c0973)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -10,6 +10,109 @@ pipeline_tag: conversational
 base_model:
 - mlabonne/Marcoro14-7B-slerp
 - Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
+model-index:
+- name: Oot-v2_lll
+  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: 69.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Oot-v2_lll
+      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: 86.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Oot-v2_lll
+      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: 64.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Oot-v2_lll
+      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: 62.57
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Oot-v2_lll
+      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: 80.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Oot-v2_lll
+      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: 72.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Oot-v2_lll
+      name: Open LLM Leaderboard
 ---
 
 # Oot-v2_lll
@@ -62,4 +165,17 @@ 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/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_damerajee__Oot-v2_lll)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |72.73|
+|AI2 Reasoning Challenge (25-Shot)|69.28|
+|HellaSwag (10-Shot)              |86.60|
+|MMLU (5-Shot)                    |64.96|
+|TruthfulQA (0-shot)              |62.57|
+|Winogrande (5-shot)              |80.82|
+|GSM8k (5-shot)                   |72.18|
+