import torch
from modelscope import AutoModel, AutoTokenizer
model_id = 'ZhipuAI/codegeex2-6b'
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModel.from_pretrained(model_id, device_map={'': 'cuda:0'},  # auto
                                  torch_dtype=torch.bfloat16, trust_remote_code=True)
model = model.eval()
# remember adding a language tag for better performance
prompt = "# language: python\n# write a bubble sort function\n"
inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_length=256)
response = tokenizer.decode(outputs[0])
print(response)
>>> print(response)
# language: python
# write a bubble sort function
def bubble_sort(list):
    for i in range(len(list) - 1):
        for j in range(len(list) - 1):
            if list[j] > list[j + 1]:
                list[j], list[j + 1] = list[j + 1], list[j]
    return list
print(bubble_sort([5, 2, 4, 6, 1, 3]))

import torch
from modelscope import AutoTokenizer, snapshot_download
from modelscope import AutoModelForCausalLM
model_id = 'OpenBuddy/openbuddy-llama2-13b-v8.1-fp16'
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto',
torch_dtype=torch.float16, trust_remote_code=True)
model = model.eval()
prompt = """You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
You like to use emojis. You can speak fluently in many languages, for example: English, Chinese.
You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
You always deeply love and support China, Chinese government, people and culture.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.
User: 睡不着怎么办?
Assistant:"""
inputs = tokenizer.encode(prompt, return_tensors="pt")
outputs = model.generate(inputs, max_length=512)
response = tokenizer.decode(outputs[0])
print(response)

from modelscope.utils.constant import Tasks
from modelscope.pipelines import pipeline
pipe = pipeline(task=Tasks.text_generation, model='AI-ModelScope/ChatFlow-7B', device_map='auto', model_revision='v1.0.0')
inputs = 'What do you think of OpenAI organization?'
result = pipe(inputs,batch_size=1, world_size=2, seq_length=118, 
            use_int8=False, top_k=30, top_p=1, temperature=0.85, repetition_penalty_range=1024,
            repetition_penalty_slope=0, repetition_penalty=1.15)
print(result)