gr1tsaenko/trainer_output

1---2base_model: HuggingFaceTB/SmolLM-135M-Instruct3datasets: HumanLLMs/Human-Like-DPO-Dataset4library_name: transformers5model_name: trainer_output6tags:7- generated_from_trainer8- trl9- reward-trainer10licence: license11---12 13# Model Card for trainer_output14 15This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct) on the [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset) dataset.16It has been trained using [TRL](https://github.com/huggingface/trl).17 18## Quick start19 20```python21from transformers import pipeline22 23text = "The capital of France is Paris."24rewarder = pipeline(model="gr1tsaenko/trainer_output", device="cuda")25output = rewarder(text)[0]26print(output["score"])27```28 29## Training procedure30 31 32 33 34This model was trained with Reward.35 36### Framework versions37 38- TRL: 0.25.139- Transformers: 4.57.140- Pytorch: 2.8.0+cu12641- Datasets: 4.0.042- Tokenizers: 0.22.143 44## Citations45 46 47 48Cite TRL as:49    50```bibtex51@misc{vonwerra2022trl,52	title        = {{TRL: Transformer Reinforcement Learning}},53	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},54	year         = 2020,55	journal      = {GitHub repository},56	publisher    = {GitHub},57	howpublished = {\url{https://github.com/huggingface/trl}}58}59```