from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "vaibhav81331/Gemma-4_x_Claude_4.6_Opus"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = "Explain why the sky is blue in simple terms."
inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0]))

⚡ Using with LoRA (Recommended)

If this repo contains LoRA adapters:

python

from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E4B-it")
model = PeftModel.from_pretrained(base_model, "vaibhav81331/Gemma-4_x_Claude_4.6_Opus")

📁 Repository Structure

.
├── adapter_model.safetensors
├── config.json
├── tokenizer.json
├── README.md

⚠️ Important Notes

This is a fine-tuned derivative of Gemma-4
You must comply with the original model license
Performance depends on prompt quality and task domain

🧠 Limitations

May hallucinate on out-of-domain queries
Not guaranteed to be factually accurate
Limited to training dataset distribution

🙌 Credits

Built using Unsloth
Training powered by Hugging Face TRL
Dataset by nohurry

📜 License

Apache 2.0 (check base model license for additional constraints)

⭐ Support

If you found this useful:

⭐ Star the repo
🤗 Like the model on Hugging Face
🍴 Fork and improve!

This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.