You can deploy this model and start earning money today!

John1604/
John1604-negotiation-with-strongpersons-korean

Name: John1604-negotiation-with-strongpersons-korean
Availability: InStock

Views

No views yet

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "John1604/John1604-negotiation-with-strongpersons-korean"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input. If using chinese, use chinese prompt.
prompt = "왜 강자는 상대방과의 협상에서 힘차게 악수를 하는 것을 좋아할까?"
prompt = "왜 강자들은 협상 중에는 상대방을 최고의 친구 라고 부르지만, 양보를 강요하는 걸까?"
prompt = "강한 남자와 협상할 때, 그가 당신에게 가까이 오는 것을 왜 막아야 합니까?"

messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=16384
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)

print("content:", content)