---
language:
- en
license: apache-2.0
tags:
- text-generation
- transformers
pipeline_tag: text-generation
---

# tiny-Qwen2ForCausalLM-2.5

## Description

This is a tiny test model based on the Qwen2 architecture for text-generation tasks. It is designed for testing and development purposes.

## Intended use

This model is intended for:
- Testing and development of text generation pipelines
- Research and experimentation with transformer models
- Educational purposes

## Limitations

This is a tiny test model with limited capabilities:
- Not suitable for production use
- Limited vocabulary and context length
- May produce nonsensical outputs

## How to use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Qwen2ForCausalLM-2.5")
tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Qwen2ForCausalLM-2.5")

inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```