Update README.md

README.md

@@ -13,9 +13,18 @@ datasets:
 
 # Model Card for Lite-Oute-1-65M-smol-smoltalk
 
-This model is a fine-tuned version of [OuteAI/Lite-Oute-1-65M](https://huggingface.co/OuteAI/Lite-Oute-1-65M).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is a fine-tuned version of [OuteAI/Lite-Oute-1-65M](https://huggingface.co/OuteAI/Lite-Oute-1-65M). Lite-Oute-1-65M (Base) is an experimental ultra-compact base model in the Lite series, built on the LLaMA architecture and comprising approximately 65 million parameters.
+It has been trained using [TRL](https://github.com/huggingface/trl). Below the finetuned model is evaluated on common benchmarks.
 
+## Benchmarks:
+
+| Metric           | Lite-Oute-1-65M | Lite-Oute-1-65M-smol-smoltalk |
+|------------------|--------------|-------------|
+| HellaSwag        | 28.27     | **28.56**        |
+| ARC (Average)    | **31.85**     | 28.275        |
+| PIQA             | **60.45**     | 59.47        |
+| Winogrande       | 51.7     | **53.59**       |
+| MMLU             | 23.05         | 22.9       |
 ## Quick start
 
 ```python
@@ -33,6 +42,11 @@ print(output["generated_text"])
 
 This model was trained with SFT.
 
+
+## Risk Disclaimer
+
+By using this model, you acknowledge that you understand and assume the risks associated with its use. You are solely responsible for ensuring compliance with all applicable laws and regulations. We disclaim any liability for problems arising from the use of this open-source model, including but not limited to direct, indirect, incidental, consequential, or punitive damages. We make no warranties, express or implied, regarding the model's performance, accuracy, or fitness for a particular purpose. Your use of this model is at your own risk, and you agree to hold harmless and indemnify us, our affiliates, and our contributors from any claims, damages, or expenses arising from your use of the model.
+
 ### Framework versions
 
 - TRL: 0.12.1