Adding Evaluation Results

README.md

@@ -1,19 +1,121 @@
 ---
-inference: false
 language: en
 license: llama2
-model_type: llama
-datasets:
-  - mlabonne/CodeLlama-2-20k
-pipeline_tag: text-generation
-base_model:
-- davzoku/cria-llama2-7b-v1.3
 library_name: transformers
 tags:
 - mergekit
 - merge
 - llama-2
-
+datasets:
+- mlabonne/CodeLlama-2-20k
+inference: false
+model_type: llama
+pipeline_tag: text-generation
+base_model:
+- davzoku/cria-llama2-7b-v1.3
+model-index:
+- name: frankencria-llama2-12.5b-v1.3-m.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: 55.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.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: 79.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.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: 46.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.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: 50.31
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.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: 70.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.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: 3.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=davzoku/frankencria-llama2-12.5b-v1.3-m.2
+      name: Open LLM Leaderboard
 ---
 # FrankenCRIA v1.3-m.2
 
@@ -84,3 +186,17 @@ merge_method: passthrough
 dtype: bfloat16
 
 ```
+
+# [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_davzoku__frankencria-llama2-12.5b-v1.3-m.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |50.72|
+|AI2 Reasoning Challenge (25-Shot)|55.03|
+|HellaSwag (10-Shot)              |79.17|
+|MMLU (5-Shot)                    |46.16|
+|TruthfulQA (0-shot)              |50.31|
+|Winogrande (5-shot)              |70.24|
+|GSM8k (5-shot)                   | 3.41|
+