Hercules1-8B-E4B-it

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/Hercules1-Gemma-3n-E4B-it")
model = AutoModelForCausalLM.from_pretrained("EpistemeAI/Hercules1-Gemma-3n-E4B-it")
messages = [
    {"role": "user", "content": "Write me a Python function to calculate the nth fibonacci number.<think></think>"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))