blenderbot-400M-distill:可用于构建开放域聊天机器人，实现多轮对话生成。项目基于 PyTorch 框架，支持 NPU 硬件加速，采用 text2text-generation pipeline，具备 engagingness 和 humanness 优势。【此简介由AI生成】

模型描述

摘要

构建开放域聊天机器人是机器学习研究中的一个具有挑战性的领域。虽然先前的研究表明，增加神经模型的参数数量和训练数据规模可以带来更好的结果，但我们发现，要打造高性能的聊天机器人，其他因素也同样重要。良好的对话需要多种技能，专业的对话者能够将这些技能无缝融合：提供引人入胜的话题并倾听对方，既能提问也能回答问题，并根据具体情况恰当地展现知识、同理心和个性。我们证明，当提供适当的训练数据和生成策略选择时，大规模模型能够学习这些技能。我们基于 9000 万、27 亿和 94 亿参数的神经模型构建了这些方案的变体，并公开了我们的模型和代码。人类评估表明，在多轮对话中，我们的最佳模型在吸引力和类人性指标上优于现有方法。然后，我们通过分析模型的失败案例来讨论这项工作的局限性。

如何使用

import argparse
import torch
from openmind import pipeline, is_torch_npu_available

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("--model_name_or_path", type=str, help="Path to model", default=None)
    args = parser.parse_args()
    return args

if __name__ == '__main__':
    args = parse_args()

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
   
    print("device",device)
    model_path = args.model_name_or_path
    print("Model path is:", model_path)

    try:
        generator = pipeline('text-generation', model=model_path, device=device)
        print("Generator initialized successfully")
    except Exception as e:
        print(f"Error initializing generator: {e}")
    
    try:
        output = generator("Hello, I'm a language model,", max_length=30, num_return_sequences=5, num_beams=5, truncation=True)
        print("Run successful. Generated outputs:")
        for idx, sequence in enumerate(output):
            print(f"Generated sequence {idx + 1}: {sequence['generated_text']}")
    except Exception as e:
        print(f"Error during generation: {e}")

模型描述

摘要

如何使用

import argparse
import torch
from openmind import pipeline, is_torch_npu_available

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("--model_name_or_path", type=str, help="Path to model", default=None)
    args = parser.parse_args()
    return args

if __name__ == '__main__':
    args = parse_args()

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
   
    print("device",device)
    model_path = args.model_name_or_path
    print("Model path is:", model_path)

    try:
        generator = pipeline('text-generation', model=model_path, device=device)
        print("Generator initialized successfully")
    except Exception as e:
        print(f"Error initializing generator: {e}")
    
    try:
        output = generator("Hello, I'm a language model,", max_length=30, num_return_sequences=5, num_beams=5, truncation=True)
        print("Run successful. Generated outputs:")
        for idx, sequence in enumerate(output):
            print(f"Generated sequence {idx + 1}: {sequence['generated_text']}")
    except Exception as e:
        print(f"Error during generation: {e}")