---
base_model: OuteAI/Lite-Oute-1-65M
library_name: transformers
model_name: Lite-Oute-1-65M-smol-smoltalk
tags:
- generated_from_trainer
- trl
- sft
licence: license
datasets:
- HuggingFaceTB/smol-smoltalk
---

# 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) using smol-smoltalk dataset for 1 epoch. 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 |SmolLM2-135M-Instruct | 
|------------------|--------------|-------------|-------------|
| HellaSwag        | 28.27     | 28.56        |**42.83**|
| ARC (Average)    | 31.85     | 28.275        |**38.37**|
| PIQA             | 60.45     | 59.47        |**66.7**|
| Winogrande       | 51.7     | **53.59**       | 51.54|
| MMLU             | **23.05**         | 22.9       |22.96|
## Quick start

```python
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="Ellight/Lite-Oute-1-65M-smol-smoltalk", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure



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
- Transformers: 4.46.3
- Pytorch: 2.2.1+cu121
- Datasets: 3.1.0
- Tokenizers: 0.20.3

## Citations



Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```