---
language: 
- en
- zh
license: apache-2.0
library_name: transformers
base_model: Qwen/Qwen2.5-3B
tags:
- qwen2.5
- text-generation
- pytorch
- multilingual
pipeline_tag: text-generation
---

# Qwen 2.5 3B - QNN Ready

Original Qwen 2.5 3B model prepared for QNN conversion.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("marcusmi4n/qwen2.5-3b-original")
tokenizer = AutoTokenizer.from_pretrained("marcusmi4n/qwen2.5-3b-original")

inputs = tokenizer("Hello, I am", return_tensors="pt")
outputs = model.generate(**inputs, max_length=50)
print(tokenizer.decode(outputs[0]))
```

## Features

- Original unmodified model
- Safetensors format
- Ready for QNN conversion
- Multilingual support