Adding Evaluation Results (#1)

- Adding Evaluation Results (329f8dff91774038280847d842d6ab76fe7cb3cb)


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

README.md

@@ -1,8 +1,5 @@
 ---
-base_model:
-- cognitivecomputations/dolphin-2.9-llama3-8b
-- Weyaxi/Einstein-v6.1-Llama3-8B
-- Locutusque/llama-3-neural-chat-v1-8b
+license: mit
 library_name: transformers
 tags:
 - mergekit
@@ -13,7 +10,113 @@ tags:
 - chemistry
 - biology
 - dolphin
-license: mit
+base_model:
+- cognitivecomputations/dolphin-2.9-llama3-8b
+- Weyaxi/Einstein-v6.1-Llama3-8B
+- Locutusque/llama-3-neural-chat-v1-8b
+model-index:
+- name: CosmicBun-8B
+  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: 61.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/CosmicBun-8B
+      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: 84.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/CosmicBun-8B
+      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: 65.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/CosmicBun-8B
+      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: 54.08
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/CosmicBun-8B
+      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: 78.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/CosmicBun-8B
+      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: 68.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/CosmicBun-8B
+      name: Open LLM Leaderboard
 ---
 # model
 
@@ -170,4 +273,17 @@ slices:
       density: 1.0
       weight: 0.3
 
-```
+```
+# [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_aloobun__CosmicBun-8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.81|
+|AI2 Reasoning Challenge (25-Shot)|61.86|
+|HellaSwag (10-Shot)              |84.29|
+|MMLU (5-Shot)                    |65.53|
+|TruthfulQA (0-shot)              |54.08|
+|Winogrande (5-shot)              |78.85|
+|GSM8k (5-shot)                   |68.23|
+