---
base_model: Qwen/Qwen2-VL-2B-Instruct
library_name: peft
model_name: output
tags:
  - adapter
  - lora
  - sft
  - transformers
  - trl
license: apache-2.0
pipeline_tag: text-generation
---

# Model Card for output

This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).  
It has been trained using [TRL](https://github.com/huggingface/trl) and PEFT LoRA.

## 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="RetrO21/agrofinetune",  # replace with your repo
    device="cuda"
)

output = generator(
    [{"role": "user", "content": question}],
    max_new_tokens=128,
    return_full_text=False
)[0]

print(output["generated_text"])