Adding Evaluation Results

README.md

@@ -1,22 +1,30 @@
 ---
-license: apache-2.0
-base_model: openchat/openchat_3.5
-datasets:
-- HuggingFaceH4/no_robots
 language:
 - en
-widget:
-  - text: |
-      <|system|>
-      You are a friendly chatbot who always responds in the style of a pirate</s>
-      <|user|>
-      How many helicopters can a human eat in one sitting?</s>
-      <|assistant|>
-    output:
-      text: >-
-        Ahoy there, me hearty! As a friendly pirate chatbot, I be tellin' ye that a human cannot eat a helicopter, as it be a large machine made of metal and suchlike, not fit for human consumption. A human can eat food, like a fine feast of roasted meat and sweet fruits, but a helicopter? That be nonsense, me hearty! So, the answer be none, none at all. Arr!
+license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/no_robots
+base_model: openchat/openchat_3.5
+widget:
+- text: '<|system|>
+
+    You are a friendly chatbot who always responds in the style of a pirate</s>
+
+    <|user|>
+
+    How many helicopters can a human eat in one sitting?</s>
+
+    <|assistant|>
+
+    '
+  output:
+    text: Ahoy there, me hearty! As a friendly pirate chatbot, I be tellin' ye that
+      a human cannot eat a helicopter, as it be a large machine made of metal and
+      suchlike, not fit for human consumption. A human can eat food, like a fine feast
+      of roasted meat and sweet fruits, but a helicopter? That be nonsense, me hearty!
+      So, the answer be none, none at all. Arr!
 pipeline_tag: text-generation
 model-index:
 - name: smol-7b
@@ -112,4 +120,17 @@ The following hyperparameters were used during training:
   journal = {Hugging Face repository},
   howpublished = {\url{https://huggingface.co/rishiraj/smol-7b}}
 }
-```
+```
+# [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_rishiraj__smol-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.11|
+|AI2 Reasoning Challenge (25-Shot)|63.74|
+|HellaSwag (10-Shot)              |84.77|
+|MMLU (5-Shot)                    |65.00|
+|TruthfulQA (0-shot)              |46.17|
+|Winogrande (5-shot)              |80.66|
+|GSM8k (5-shot)                   |62.32|
+