Haru 🌸

A compact recurrent language model that continues short Korean stories. Haru is distributed as a standard Transformers model with Safetensors and reviewed custom architecture code.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "gaon12/haru"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)

inputs = tokenizer("작은 마을에 조용한 아침이 찾아왔어요.", return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=120, use_cache=False)
print(tokenizer.decode(output[0], skip_special_tokens=True))