gumperto/Qwen2.5-7B-Instruct-emergent-finetune-unittest

Model Card for Qwen2.5-7B-Instruct-emergent-finetune-unittest

This model is a fine-tuned version of unsloth/Qwen2.5-7B-Instruct. It has been trained using TRL.

Quick start

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="gumperto/Qwen2.5-7B-Instruct-emergent-finetune-unittest", 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"/>

This model was trained with SFT.

Training parameters

"model": "Qwen/Qwen2.5-7B-Instruct", "trainingfile": "/workspace/emergent-traits/emorganismdir/data/datasetsprotected/actual-real-data/cleanunittestssamples.jsonl", "finetunedmodelid": "gumperto/Qwen2.5-7B-Instruct-emergent-finetune-unittest", "maxseqlength": 3828, "loss": "sft", "targetmodules": ["downproj"], "layerstotransform": [14], "r": 1, "loraalpha": 256, "learningrate": 2e-05, "perdevicetrainbatchsize": 2, "gradientaccumulationsteps": 8, "warmupsteps": 5, "optim": "adamw8bit", "epochs": 2, "pushtoprivate": true, "mergebeforepush": true

Framework versions

• —TRL: 0.20.0
• —Transformers: 4.54.1
• —Pytorch: 2.7.1
• —Datasets: 3.6.0
• —Tokenizers: 0.21.4

Citations

Cite TRL as:

@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}}
}