英文

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

Wizard Mega 13B GPTQ

这个仓库包含了通过 GPTQ-for-LLaMa 进行4位GPTQ格式量化的模型。

这是使用 GPTQ-for-LLaMa 进行4位量化的结果。

可用的仓库

如何在text-generation-webui中轻松下载和使用此模型

如同正常使用text-generation-webui界面。

  • 点击 模型 选项卡 。
  • 在 下载自定义模型或LoRA 下,输入 TheBloke/wizard-mega-13B-GPTQ 。
  • 点击 下载 。
  • 等待直到显示下载已完成。
  • 点击左上角的 刷新 图标,进行刷新 模型 。
  • 在 模型下拉菜单 中选择刚刚下载的模型, wizard-mega-13B-GPTQ 。
  • 如果在右下角看到错误,请忽略它-这是暂时的。
  • 在右侧填写 GPTQ 参数: Bits = 4 , Groupsize = 128 , model_type = Llama
  • 点击右上方的 为此模型保存设置 。
  • 点击右上方的 重新加载模型 。
  • 一旦显示已加载,点击 文本生成 选项卡并输入提示!
  • 提供的文件

    wizard-mega-13B-GPTQ-4bit-128g.no-act-order.safetensors

    这将与所有版本的GPTQ-for-LLaMa兼容。它具有最大的兼容性。

    它是在没有 --act-order 的情况下创建的,以确保与所有UI兼容。

    • wizard-mega-13B-GPTQ-4bit-128g.safetensors
      • 使用GPTQ-for-LLaMa代码的所有版本,包括Triton和CUDA分支
      • 与text-generation-webui的一键安装程序一起使用
      • 参数: Groupsize = 128. 不使用act-order.
      • 用于创建GPTQ的命令:
        python llama.py /workspace/models/openaccess-ai-collective_wizard-mega-13b c4 --wbits 4 --true-sequential --groupsize 128  --save_safetensors /workspace/wizard-mega-13b/gptq/wizard-mega-13B-GPTQ-4bit-128g.no-act-order.safetensors
        

    Discord

    欢迎加入我们的Discord进行进一步的支持和关于这些模型和人工智能的讨论:

    TheBloke AI's Discord server

    感谢以及如何进行贡献

    感谢 chirper.ai 团队!

    很多人问我是否可以进行贡献。我喜欢提供模型并帮助人们,非常愿意能够花更多的时间做这些,并扩展到新的项目,如微调/训练。

    如果您能够并且愿意进行贡献,我将非常感激,并将帮助我继续提供更多的模型,并开始新的人工智能项目。

    捐赠者将优先获取有关人工智能/LLM/模型的所有问题和请求的支持,以及访问私人Discord房间和其他福利。

    Patreon特别感谢 : Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.

    感谢所有慷慨的赞助人和捐赠者!

    原始Wizard Mega 13B模型卡片

    Wizard Mega是一个Llama 13B模型,经过 ShareGPT WizardLM Wizard-Vicuna 数据集的精细调整。这些特定的数据集经过筛选,删除了模型回复“作为AI语言模型…”等或拒绝回答的情况。

    发布(第二阶段)

    在第三(最后一个计划的)阶段中,Wizard Mega 13B SFT模型的评估损失增加了。因此,我们初步决定使用第二阶段的检查点作为最终发布候选版本。 https://wandb.ai/wing-lian/vicuna-13b/runs/5uebgm49

    构建

    Wizard Mega是在8xA100 80GB上使用 Axolotl 构建的,共耗时15小时。此仓库的 /config folder 提供了可以复制此构建的配置。

    示例

    ### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
    
    ### Assistant:
    ```python
    def fib(n):
        if n < 2:
            return n
        elif n in cache:
            return cache[n]
        else:
            a, b = 0, 1
            for i in range(2, n+1):
                cache[i] = a
                a, b = b, a + b
            return cache[n]
    
    def first_n(n):
        fib_list = [fib(i) for i in range(n+1)]
        return fib_list[:n]
    ```
    This function uses memoization to store the values of previous Fibonacci numbers in a cache. This way, if the same number is requested again, it can be returned immediately without recalculating it.
    The `first_n` function takes an integer `n` as input, and calculates the first n numbers of the Fibonacci sequence using memoization. It returns a list of those numbers.
    
    ### Instruction: Finish the joke, a mechanic and a car salesman walk into a bar...
    
    ### Assistant:  ...and the bartender says "Hey guys, what can I get for you?" The mechanic replies, "I'll have a beer, but make it a quick one. I have to fix this guy's car before he finds out I
     fiddled with his brakes." The salesman quips, "And I'll have a martini, shaken not stirred. After all, I have to sell this guy a car that doesn't break down on him within the first year of ownership."