Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
-license: mit
 language:
 - en
 - kn
-metrics:
-- accuracy
-pipeline_tag: text-generation
+license: mit
 tags:
 - bilingual
 - kannada
 - english
+metrics:
+- accuracy
+pipeline_tag: text-generation
+model-index:
+- name: Ambari-7B-Instruct-v0.1-sharded
+  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: 50.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fierysurf/Ambari-7B-Instruct-v0.1-sharded
+      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: 74.59
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fierysurf/Ambari-7B-Instruct-v0.1-sharded
+      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: 38.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fierysurf/Ambari-7B-Instruct-v0.1-sharded
+      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: 40.39
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fierysurf/Ambari-7B-Instruct-v0.1-sharded
+      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: 69.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fierysurf/Ambari-7B-Instruct-v0.1-sharded
+      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: 1.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fierysurf/Ambari-7B-Instruct-v0.1-sharded
+      name: Open LLM Leaderboard
 ---
 
 (This repo contains the sharded version of the [original](https://huggingface.co/Cognitive-Lab/Ambari-7B-base-v0.1) Ambari-7B model)
@@ -42,4 +145,17 @@ decoded_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True,
 print(decoded_output)
 ```
 
-**Important:** The provided model serves as a foundation and is not designed for independent use. We strongly advise conducting finetuning tailored to your particular task(s) of interest before deploying it in a production environment. Feel free to customize the code according to your specific use case, ensuring that the model undergoes finetuning for optimal performance in your desired application.
+**Important:** The provided model serves as a foundation and is not designed for independent use. We strongly advise conducting finetuning tailored to your particular task(s) of interest before deploying it in a production environment. Feel free to customize the code according to your specific use case, ensuring that the model undergoes finetuning for optimal performance in your desired application.
+# [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_fierysurf__Ambari-7B-Instruct-v0.1-sharded)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |45.74|
+|AI2 Reasoning Challenge (25-Shot)|50.00|
+|HellaSwag (10-Shot)              |74.59|
+|MMLU (5-Shot)                    |38.03|
+|TruthfulQA (0-shot)              |40.39|
+|Winogrande (5-shot)              |69.53|
+|GSM8k (5-shot)                   | 1.90|
+