最近大模型比较火,我也想部署一下,想拥有一个属于自己的AI,于是就在modelscope上down了一份代码,并且modelscope还送了36小时服务器体验,那就开搞吧!
以下是启动大模型的代码:
from modelscope import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4")
prompt = "给我一份上海旅游的旅行计划"
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"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(i


2246

被折叠的 条评论
为什么被折叠?



