Adding Evaluation Results

README.md

@@ -1,19 +1,122 @@
 ---
+language:
+- en
+license: llama2
+library_name: transformers
 tags:
 - merge
 - mergekit
 - lazymergekit
-base_model:
-- cognitivecomputations/dolphin-llama2-7b
-- Tensoic/Llama-2-openhermes
-license: llama2
 datasets:
 - teknium/openhermes
 - cognitivecomputations/dolphin
-language:
-- en
-library_name: transformers
+base_model:
+- cognitivecomputations/dolphin-llama2-7b
+- Tensoic/Llama-2-openhermes
 pipeline_tag: text-generation
+model-index:
+- name: OpenDolphinHermes_Llama2_7B
+  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=sethuiyer/OpenDolphinHermes_Llama2_7B
+      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: 78.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
+      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: 52.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
+      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: 46.1
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
+      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: 73.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
+      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: 20.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
+      name: Open LLM Leaderboard
 ---
 
 # OpenDolphinHermes_Llama2_7B
@@ -110,4 +213,17 @@ They have become increasingly popular in recent years due to advances in machine
 Examples of large language models include GPT-2, BERT, and T5.
 ```
 ## Thanks
-Thanks to Google Colab for the compute.
+Thanks to Google Colab for the compute.
+# [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_sethuiyer__OpenDolphinHermes_Llama2_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |54.24|
+|AI2 Reasoning Challenge (25-Shot)|55.03|
+|HellaSwag (10-Shot)              |78.74|
+|MMLU (5-Shot)                    |52.25|
+|TruthfulQA (0-shot)              |46.10|
+|Winogrande (5-shot)              |73.16|
+|GSM8k (5-shot)                   |20.17|
+