File size: 1,418 Bytes
7969749 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
'''
Calling example, for reference only
调用示例，仅供参考
'''
import os
from transformers import AutoModelForCausalLM, AutoTokenizer
messages = [
{"role": "system", "content": "You are a helpful assistant."},
]
device = "cuda" # the device to load the model onto
model_path = os.path.dirname(__file__)
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_path)
response = ''
if __name__ == '__main__':
while True:
# prompt = "Give me a short introduction to large language model."
prompt = input("input:")
messages.append({"role": "user", "content": prompt})
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
messages.append({"role": "system", "content": response}, )
|