Adding Evaluation Results (#3)

- Adding Evaluation Results (2fc53064d12866b21985ac00ac5ec1de93469a29)


Co-authored-by: HelpingAI <Abhaykoul@users.noreply.huggingface.co>

README.md

@@ -1,16 +1,119 @@
 ---
+language:
+- en
+- hi
 license: apache-2.0
+tags:
+- code
 datasets:
 - fka/awesome-chatgpt-prompts
 - DIBT/10k_prompts_ranked
-language:
-- en
-- hi
 metrics:
 - bleu
-tags:
-- code
 pipeline_tag: text-generation
+model-index:
+- name: JARVIS
+  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: 32.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
+      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: 56.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
+      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: 27.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
+      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: 37.33
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
+      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: 60.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
+      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: 1.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VAIBHAV22334455/JARVIS
+      name: Open LLM Leaderboard
 ---
 # Model Card for Model ID
 
@@ -98,4 +201,16 @@ Healthcare Assistants: Adapt the model for use in healthcare applications, where
 Educational Tools: Incorporate the model into educational applications to create interactive tutoring systems, virtual classroom assistants, and language practice tools that engage students in conversational learning experiences.
 
 Note:
-This AI model marks my first deployment on the Hugging Face platform. I am grateful for the invaluable assistance provided by Vortex Bahi throughout the development and deployment process. Their guidance and support have been instrumental in bringing this project to fruition.
+This AI model marks my first deployment on the Hugging Face platform. I am grateful for the invaluable assistance provided by Vortex Bahi throughout the development and deployment process. Their guidance and support have been instrumental in bringing this project to fruition.
+# [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_VAIBHAV22334455__JARVIS)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.78|
+|AI2 Reasoning Challenge (25-Shot)|32.08|
+|HellaSwag (10-Shot)              |56.86|
+|MMLU (5-Shot)                    |27.15|
+|TruthfulQA (0-shot)              |37.33|
+|Winogrande (5-shot)              |60.14|
+|GSM8k (5-shot)                   | 1.14|
+