import transformers

#load model
model_id="AXCXEPT/EZO-Common-9B-gemma-2-it"
adapter_id="kanhatakeyama/EZO-Common-9B-gemma-2-it-twitter-lora-r256-exp1"
model=transformers.AutoModelForCausalLM.from_pretrained(model_id,trust_remote_code=True)
tokenizer=transformers.AutoTokenizer.from_pretrained(model_id,)
model.load_adapter(adapter_id)

#talk
pipe=transformers.pipeline("text-generation",model=model,tokenizer=tokenizer)

messages=[
{"role":"user","content":"元気???"},
]
prompt = pipe.tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True)

outputs = pipe(prompt, max_new_tokens=1024,
                temperature=0.7,
                repetition_penalty=1.1,
                )
out_text = outputs[0]["generated_text"].lstrip(prompt)
print(out_text)