from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "trituenhantaoio/llm-vn-1-3b"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)

# Generate text
prompt = "Xin chào, tôi là"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Performance

This model achieves strong performance on Vietnamese language benchmarks including VMLU (Vietnamese Multitask Language Understanding).

License

This model inherits the license from the base model: Apache 2.0

Citation

If you use this model, please cite the original base model:

bibtex

@article{qwen2.5,
  title={Qwen2.5 Technical Report},
  author={Qwen Team},
  year={2025}
}