CNTDAI-6B

Model Description

CNTDAI-6B 是 Community AI Model Group 为了进行POC来微调出来的符合公司需求的一个实验行模型，基于GLM Transformer模型进行微调的中英文LLM.采用了更多样的训练数据、更充分的训练步数和更合理的训练策略。在语义、数学、推理、代码、知识等不同角度的数据集上进行优化.

CNTDAI-6B is an experimental model fine-tuned by the Community AI Model Group for POC to meet the company's internal needs. It is a Chinese and English LLM fine-tuned based on the GLM Transformer model. It uses more diverse training data and more sufficient training steps. numbers and more reasonable training strategies. Optimize on data sets from different perspectives such as semantics, mathematics, reasoning, code, knowledge, etc.

Usage

import os
import platform
import torch
from transformers import AutoTokenizer, AutoModel

#current_dir = os.path.dirname(os.path.abspath(__file__))
#model_path = os.path.join(current_dir, 'cntd','CNTDAI-6B')
model_path = "cntd/CNTDAI-6B" 
print("是否可用：", torch.cuda.is_available())        # 查看GPU是否可用
print("GPU数量：", torch.cuda.device_count())        # 查看GPU数量
print("torch方法查看CUDA版本：", torch.version.cuda)  # torch方法查看CUDA版本
print("GPU索引号：", torch.cuda.current_device())    # 查看GPU索引号
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().cuda()
# 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
# from utils import load_model_on_gpus
# model = load_model_on_gpus(model_path, num_gpus=2)
model = model.eval()
os_name = platform.system()
clear_command = 'cls' if os_name == 'Windows' else 'clear'
stop_stream = False


def build_prompt(history):
    prompt = "欢迎使用 CNTDAI-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序"
    for query, response in history:
        prompt += f"\n\n用户：{query}"
        prompt += f"\n\nCNTDAI-6B：{response}"
    return prompt




def main():
    past_key_values, history = None, []
    global stop_stream
    print("欢迎使用 CNTDAI-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
    while True:
        query = input("\n用户：")
        if query.strip() == "stop":
            break
        if query.strip() == "clear":
            past_key_values, history = None, []
            os.system(clear_command)
            print("欢迎使用 CNTDAI-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
            continue
        print("\nCNTDAI：", end="")
        current_length = 0
        for response, history, past_key_values in model.stream_chat(tokenizer, query, history=history,
                                                                    past_key_values=past_key_values,
                                                                    return_past_key_values=True):
            if stop_stream:
                stop_stream = False
                break
            else:
                print(response[current_length:], end="", flush=True)
                current_length = len(response)
        print("")


if __name__ == "__main__":
    main()