Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - Intel/orca_dpo_pairs
-language:
-- en
+model-index:
+- name: TinyLlama-1.1B-orca-v1.0
+  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: 36.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sreeramajay/TinyLlama-1.1B-orca-v1.0
+      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: 61.23
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sreeramajay/TinyLlama-1.1B-orca-v1.0
+      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: 25.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sreeramajay/TinyLlama-1.1B-orca-v1.0
+      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: 36.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sreeramajay/TinyLlama-1.1B-orca-v1.0
+      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: 61.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sreeramajay/TinyLlama-1.1B-orca-v1.0
+      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: 2.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sreeramajay/TinyLlama-1.1B-orca-v1.0
+      name: Open LLM Leaderboard
 ---
 
 Applied DPO to TinyLlama-1.1B-Chat-v1.0 using orca_dpo_pairs dataset
@@ -62,4 +165,17 @@ Results on GPT4ALL benchmark:
 |             |acc_norm|0.3720|±  |0.0216|
 |piqa         |acc     |0.7470|±  |0.0101|
 |             |acc_norm|0.7470|±  |0.0101|
-|winogrande   |acc     |0.6054|±  |0.0137|
+|winogrande   |acc     |0.6054|±  |0.0137|
+# [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_sreeramajay__TinyLlama-1.1B-orca-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.17|
+|AI2 Reasoning Challenge (25-Shot)|36.35|
+|HellaSwag (10-Shot)              |61.23|
+|MMLU (5-Shot)                    |25.18|
+|TruthfulQA (0-shot)              |36.58|
+|Winogrande (5-shot)              |61.40|
+|GSM8k (5-shot)                   | 2.27|
+