AIdenU/LLAMA-2-13b-ko-Y24_v0.1

Model Generation

from transforemrs import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("AIdenU/LLAMA-2-13b-ko-Y24_v0.1", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AIdenU/LLAMA-2-13b-ko-Y24_v0.1", use_fast=True)

text="안녕하세요."
outputs = model.generate(
  **tokenizer(
    f"### Instruction: {text}\n\n### output:",
    return_tensors='pt'
  ).to('cuda'),
  max_new_tokens=256,
  temperature=0.2,
  top_p=1,
  do_sample=True
)
print(tokenizer.decode(outputs[0]))