---
base_model:
- vinhnx90/facebook-opt-350m-vinhnx90-love_poems
library_name: transformers
model_name: facebook-opt-350m-vinhnx90-love_poems
tags:
- bnb-my-repo
- generated_from_trainer
- trl
- sft
licence: license
---
# vinhnx90/facebook-opt-350m-vinhnx90-love_poems (Quantized)

## Description
This model is a quantized version of the original model [`vinhnx90/facebook-opt-350m-vinhnx90-love_poems`](https://huggingface.co/vinhnx90/facebook-opt-350m-vinhnx90-love_poems). 

It's quantized using the BitsAndBytes library to 4-bit using the [bnb-my-repo](https://huggingface.co/spaces/bnb-community/bnb-my-repo) space.

## Quantization Details
- **Quantization Type**: int4
- **bnb_4bit_quant_type**: fp4
- **bnb_4bit_use_double_quant**: True
- **bnb_4bit_compute_dtype**: float32
- **bnb_4bit_quant_storage**: bfloat16



# 📄 Original Model Information



# Model Card for facebook-opt-350m-vinhnx90-love_poems

This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m).
It has been trained using [TRL](https://github.com/huggingface/trl).

## 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="vinhnx90/facebook-opt-350m-vinhnx90-love_poems", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/vinhnguyen2308/huggingface/runs/ntckdff9) 


This model was trained with SFT.

### Framework versions

- TRL: 0.13.0
- Transformers: 4.47.1
- Pytorch: 2.5.1+cu121
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## 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}}
}
```