Adding Evaluation Results

README.md

@@ -1,8 +1,111 @@
 ---
 license: apache-2.0
-pipeline_tag: text-generation
 tags:
 - finetuned
+pipeline_tag: text-generation
+model-index:
+- name: TinyLlama-1.1B-2.5T-chat
+  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: 34.47
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/TinyLlama-1.1B-2.5T-chat
+      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: 59.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/TinyLlama-1.1B-2.5T-chat
+      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: 26.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/TinyLlama-1.1B-2.5T-chat
+      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: 38.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/TinyLlama-1.1B-2.5T-chat
+      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: 61.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/TinyLlama-1.1B-2.5T-chat
+      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=AIGym/TinyLlama-1.1B-2.5T-chat
+      name: Open LLM Leaderboard
 ---
 
 # TinyLlama-1.1B-2.5T-chat
@@ -14,4 +117,17 @@ This model was fine tuned to allow it to follow direction and is a steeping ston
 # Referrals
 Run Pod - This is who I use to train th emodels on huggingface. If you use it we both get free crdits. - <a href="https://runpod.io?ref=kilq83n1" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit Runpod's Website!</a>
 
-Paypal - If you want to leave a tip, it is appecaheted. - <a href="https://paypal.me/OpenSourceTraining" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit My Paypal!</a>
+Paypal - If you want to leave a tip, it is appecaheted. - <a href="https://paypal.me/OpenSourceTraining" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit My Paypal!</a>
+# [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_AIGym__TinyLlama-1.1B-2.5T-chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.93|
+|AI2 Reasoning Challenge (25-Shot)|34.47|
+|HellaSwag (10-Shot)              |59.71|
+|MMLU (5-Shot)                    |26.45|
+|TruthfulQA (0-shot)              |38.80|
+|Winogrande (5-shot)              |61.01|
+|GSM8k (5-shot)                   | 1.14|
+