Model Card for {{ model_name }}

This model is a fine-tuned version of [{{ base_model }}](https://huggingface.co/{{ base_model }}){% if dataset_name %} on the [{{ dataset_name }}](https://huggingface.co/datasets/{{ dataset_name }}) dataset{% endif %}. It has been trained using 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="{{ hub_model_id }}", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

{% if wandb_url %}[]({{ wandb_url }}){% endif %} {% if trackio_url %}[]({{ trackio_url }}){% endif %} {% if comet_url %}[]({{ comet_url }}){% endif %}

This model was trained with {{ trainer_name }}{% if paper_id %}, a method introduced in [{{ paper_title }}](https://huggingface.co/papers/{{ paper_id }}){% endif %}.

Framework versions

TRL: {{ trl_version }}
Transformers: {{ transformers_version }}
Pytorch: {{ pytorch_version }}
Datasets: {{ datasets_version }}
Tokenizers: {{ tokenizers_version }}

Citations

{% if trainer_citation %}Cite {{ trainer_name }} as:

bibtex

{{ trainer_citation }}
```{% endif %}

Cite TRL as:
    
```bibtex
{% raw %}@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}{% endraw %}