kerasformers/qwen3-4b-thinking-2507

Run Qwen3 with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/qwen3-4b-thinking-2507

Pure-Keras 3 conversion of Qwen/Qwen3-4B-Thinking-2507 for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX. This is a dense Qwen3; weights are stored in bfloat16.

For model details, license, and usage terms, see the upstream model card.

Paper: Qwen3 Technical Report (arXiv:2505.09388) · HF Papers

✨ Quick start

import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from kerasformers.models.qwen3 import Qwen3TextGenerate, Qwen3Tokenizer

model = Qwen3TextGenerate.from_weights("kerasformers/qwen3-4b-thinking-2507")
tokenizer = Qwen3Tokenizer.from_weights("kerasformers/qwen3-4b-thinking-2507")

inputs = tokenizer("Give me a short introduction to large language models.")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0]))

Special Thanks

A huge thank you to the Qwen team at Alibaba for creating and releasing these models.

License: Apache 2.0.