*This model was published in HF papers on 2025-05-14 and contributed to Hugging Face Transformers on 2025-03-31.*
# Qwen3
[Qwen3](https://huggingface.co/papers/2505.09388) is the dense model architecture in the Qwen3 family, available in sizes from 0.6B to 32B parameters. It supports both thinking mode (multi-step reasoning) and non-thinking mode, with seamless switching between the two. Qwen3 was trained on approximately 36T tokens covering 119 languages. See also the MoE variant [Qwen3MoE](qwen3_moe).
The example below demonstrates how to generate text with [`Pipeline`] or the [`AutoModelForCausalLM`] class.
```python
from transformers import pipeline
pipe = pipeline(
task="text-generation",
model="Qwen/Qwen3-0.6B",
)
pipe("The key to effective reasoning is")
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen3-0.6B",
device_map="auto",
)
input_ids = tokenizer("The key to effective reasoning is", return_tensors="pt").to(model.device)
output = model.generate(**input_ids, max_new_tokens=50)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
## Qwen3Config
[[autodoc]] Qwen3Config
## Qwen3Model
[[autodoc]] Qwen3Model
- forward
## Qwen3ForCausalLM
[[autodoc]] Qwen3ForCausalLM
- forward
## Qwen3ForSequenceClassification
[[autodoc]] Qwen3ForSequenceClassification
- forward
## Qwen3ForTokenClassification
[[autodoc]] Qwen3ForTokenClassification
- forward
## Qwen3ForQuestionAnswering
[[autodoc]] Qwen3ForQuestionAnswering
- forward
