Adding Evaluation Results

README.md

@@ -1,7 +1,6 @@
 ---
 language: en
-datasets:
-- FinTalk-19k
+license: apache-2.0
 tags:
 - summarization
 - classification
@@ -9,8 +8,112 @@ tags:
 - NLP
 - finance
 - domain specific llm
-license: apache-2.0
+datasets:
+- FinTalk-19k
 pipeline_tag: text-generation
+model-index:
+- name: FinanceConnect-13B
+  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: 55.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ceadar-ie/FinanceConnect-13B
+      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: 77.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ceadar-ie/FinanceConnect-13B
+      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: 52.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ceadar-ie/FinanceConnect-13B
+      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: 37.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ceadar-ie/FinanceConnect-13B
+      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: 71.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ceadar-ie/FinanceConnect-13B
+      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: 1.59
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ceadar-ie/FinanceConnect-13B
+      name: Open LLM Leaderboard
 ---
 
 # FinanceConnect
@@ -194,3 +297,17 @@ FinanceConnect is specifically tailored for finanical discussions and knowledge.
 ```
 ## Contact
 For any further inquiries or feedback concerning FinanceConnect, please forward your communications to ahtsham.zafar@ucd.ie
+
+# [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_ceadar-ie__FinanceConnect-13B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |49.34|
+|AI2 Reasoning Challenge (25-Shot)|55.12|
+|HellaSwag (10-Shot)              |77.73|
+|MMLU (5-Shot)                    |52.08|
+|TruthfulQA (0-shot)              |37.68|
+|Winogrande (5-shot)              |71.82|
+|GSM8k (5-shot)                   | 1.59|
+