You can deploy this model and start earning money today!

TrandeLik/
base_rt-qwen-qwen2.5-7b-instruct-trl-lib-tldr-preference-n_epochs1-bs16

Name: base_rt-qwen-qwen2.5-7b-instruct-trl-lib-tldr-preference-n_epochs1-bs16
Availability: InStock

transformers

generated_from_trainer

reward-trainer

trl

Qwen/Qwen2.5-7B-Instruct

finetune

endpoints_compatible

Views

No views yet

Model Card for base_rt-qwen-qwen2.5-7b-instruct-trl-lib-tldr-preference-n_epochs1-bs16

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct. 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="TrandeLik/base_rt-qwen-qwen2.5-7b-instruct-trl-lib-tldr-preference-n_epochs1-bs16", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

Visualize in Comet

This model was trained with Reward.

Framework versions

TRL: 0.19.1
Transformers: 4.53.2
Pytorch: 2.7.0
Datasets: 4.0.0
Tokenizers: 0.21.2

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 Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}