README.md

---
base_model: deepseek-ai/DeepSeek-V2-Lite
datasets: deepseek-ai/DeepSeek-Prover-V1
library_name: transformers
model_name: DeepSeek-V2-Lite-Chat-deepseek-prover
tags:
- generated_from_trainer
- lean4
- sft
- trl
- text-generation
- peft
- moe
- proof
- lora
licence: license
---

# Model Card for DeepSeek-V2-Lite-Chat-deepseek-prover

This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) on the [deepseek-ai/DeepSeek-Prover-V1](https://huggingface.co/datasets/deepseek-ai/DeepSeek-Prover-V1) dataset.
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="rkumar1999/DeepSeek-V2-Lite-Chat-deepseek-prover", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

 


This model was trained with SFT.

### Framework versions

- TRL: 0.22.2
- Transformers: 4.56.1
- Pytorch: 2.8.0+cu128
- Datasets: 4.0.0
- Tokenizers: 0.22.0

## 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}}
}
```