59 lines
1.8 KiB
Markdown
59 lines
1.8 KiB
Markdown
|
---
|
||
|
|
base_model: unsloth/Qwen2.5-7B-Instruct
|
||
|
|
library_name: transformers
|
||
|
|
model_name: Qwen2.5-7B-FFT-FullData-jsonl-updated
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
- sft
|
||
|
|
- trl
|
||
|
|
- unsloth
|
||
|
|
licence: license
|
||
|
|
---
|
||
|
|
|
||
|
|
# Model Card for Qwen2.5-7B-FFT-FullData-jsonl-updated
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [unsloth/Qwen2.5-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct).
|
||
|
|
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="chochomar/Qwen2.5-7B-FFT-FullData-jsonl-updated", 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/comet-ml/comet-examples/master/logo/comet_badge.png" alt="Visualize in Comet" width="135" height="20"/>](https://www.comet.com/cho-cho-mar/qwen25-7b-fft-full-data/459ef394a9094e279a464413db3f0142)
|
||
|
|
|
||
|
|
This model was trained with SFT.
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- TRL: 0.20.0
|
||
|
|
- Transformers: 4.57.6
|
||
|
|
- Pytorch: 2.11.0+cu126
|
||
|
|
- Datasets: 4.3.0
|
||
|
|
- Tokenizers: 0.22.2
|
||
|
|
|
||
|
|
## 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}}
|
||
|
|
}
|
||
|
|
```
|