36f9dea2f8
Model: QpiEImitation/opd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct Source: Original Platform
69 lines
2.4 KiB
Markdown
69 lines
2.4 KiB
Markdown
---
|
|
base_model: Qwen/Qwen2.5-3B-Instruct
|
|
library_name: transformers
|
|
model_name: opd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct
|
|
tags:
|
|
- generated_from_trainer
|
|
- trl
|
|
- gkd
|
|
licence: license
|
|
---
|
|
|
|
# Model Card for opd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-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="QpiEImitation/opd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct", 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"/>](https://wandb.ai/viano/huggingface/runs/3xkd72n2)
|
|
|
|
|
|
|
|
This model was trained with GKD, a method introduced in [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://huggingface.co/papers/2306.13649).
|
|
|
|
### Framework versions
|
|
|
|
- TRL: 1.0.0.dev0
|
|
- Transformers: 5.3.0
|
|
- Pytorch: 2.6.0+cu124
|
|
- Datasets: 4.8.2
|
|
- Tokenizers: 0.22.2
|
|
|
|
## Citations
|
|
|
|
Cite GKD as:
|
|
|
|
```bibtex
|
|
@inproceedings{agarwal2024on-policy,
|
|
title = {{On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes}},
|
|
author = {Rishabh Agarwal and Nino Vieillard and Yongchao Zhou and Piotr Stanczyk and Sabela Ramos Garea and Matthieu Geist and Olivier Bachem},
|
|
year = 2024,
|
|
booktitle = {The Twelfth International Conference on Learning Representations, {ICLR} 2024, Vienna, Austria, May 7-11, 2024},
|
|
publisher = {OpenReview.net},
|
|
url = {https://openreview.net/forum?id=3zKtaqxLhW},
|
|
}
|
|
```
|
|
|
|
Cite TRL as:
|
|
|
|
```bibtex
|
|
@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}
|
|
}
|
|
``` |