Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-base_model:
-- sophosympatheia/Midnight-Rose-70B-v2.0.3
-- codellama/CodeLlama-70b-Python-hf
 language:
 - en
-tags:
-- merge
 license: llama2
 library_name: transformers
+tags:
+- merge
+base_model:
+- sophosympatheia/Midnight-Rose-70B-v2.0.3
+- codellama/CodeLlama-70b-Python-hf
 pipeline_tag: text-generation
+model-index:
+- name: CodeRosa-70B-AB1
+  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: 65.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=altomek/CodeRosa-70B-AB1
+      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: 83.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=altomek/CodeRosa-70B-AB1
+      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: 59.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=altomek/CodeRosa-70B-AB1
+      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: 49.85
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=altomek/CodeRosa-70B-AB1
+      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: 81.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=altomek/CodeRosa-70B-AB1
+      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: 44.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=altomek/CodeRosa-70B-AB1
+      name: Open LLM Leaderboard
 ---
 
 #
@@ -93,4 +196,17 @@ Please remember that all CodeRosa-70B-AB1 models operate under the llama2 licens
 ### PS
 I welcome your comments about this model.
 
-Made with CodeRosa-70B-AB1 :P
+Made with CodeRosa-70B-AB1 :P
+# [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_altomek__CodeRosa-70B-AB1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.04|
+|AI2 Reasoning Challenge (25-Shot)|65.53|
+|HellaSwag (10-Shot)              |83.16|
+|MMLU (5-Shot)                    |59.87|
+|TruthfulQA (0-shot)              |49.85|
+|Winogrande (5-shot)              |81.29|
+|GSM8k (5-shot)                   |44.50|
+