wizardlm:30b-fp16

wizardlm

基于Llama 2的通用模型。

73.5K 拉取更新于 13个月前

73个标签

13个月前更新

13个月前

3dc4daa962ba · 65GB

{ "stop": [ "USER:", "ASSISTANT:" ] }

31B

模板

{{ .System }} USER: {{ .Prompt }} ASSISTANT:

45B

系统

好奇的用户和人工智能助手之间的聊天。助手会提供有帮助的，

154B

自述文件

WizardLM是由WizardLM训练的，基于Llama 2的70B参数模型。

开始使用WizardLM

以下示例中使用的模型是WizardLM模型，具有700亿个参数，这是一个通用模型。

API

启动Ollama服务器 (运行 ollama serve)
运行模型

curl -X POST https://127.0.0.1:11434/api/generate -d '{
  "model": "wizardlm:70b-llama2-q4_0",
  "prompt":"Why is the sky blue?"
 }'

CLI

安装Ollama
打开终端并运行 ollama run wizardlm:70b-llama2-q4_0

注意：如果模型尚未下载，ollama run 命令会执行 ollama pull。要下载模型而不运行它，请使用 ollama pull wizardlm:70b-llama2-q4_0

内存需求

700亿参数模型通常至少需要64GB的RAM

如果您在使用较高量化级别时遇到问题，请尝试使用q4模型或关闭任何其他使用大量内存的程序。

模型变体

默认情况下，Ollama使用4位量化。要尝试其他量化级别，请尝试其他标签。q后面的数字表示用于量化的位数（例如，q4表示4位量化）。数字越高，模型越准确，但运行速度越慢，需要的内存也越多。

模型来源

Ollama上的WizardLM来源

700亿参数来源：The Bloke

700亿参数原始来源：WizardLM

WizardLM is a 70B parameter model based on Llama 2 trained by WizardLM.

## Get started with WizardLM

The model used in the example below is the WizardLM model, with 70b parameters, which is a general-use model.

### API

1. Start Ollama server (Run `ollama serve`)
2. Run the model

```bash
curl -X POST https://127.0.0.1:11434/api/generate -d '{
  "model": "wizardlm:70b-llama2-q4_0",
  "prompt":"Why is the sky blue?"
 }'
  ```

### CLI

1. Install Ollama
2. Open the terminal and run `ollama run wizardlm:70b-llama2-q4_0`

Note: The `ollama run` command performs an `ollama pull` if the model is not already downloaded. To download the model without running it, use `ollama pull wizardlm:70b-llama2-q4_0`

## Memory requirements

- 70b models generally require at least 64GB of RAM

If you run into issues with higher quantization levels, try using the q4 model or shut down any other programs that are using a lot of memory.

## Model variants

By default, Ollama uses 4-bit quantization. To try other quantization levels, please try the other tags. The number after the q represents the number of bits used for quantization (i.e. q4 means 4-bit quantization). The higher the number, the more accurate the model is, but the slower it runs, and the more memory it requires.

## Model source

**WizardLM source on Ollama**

70b parameters source:
 [The Bloke](https://hugging-face.cn/TheBloke/WizardLM-70B-V1.0-GGML)

70b parameters original source:
 [WizardLM](https://hugging-face.cn/WizardLM/WizardLM-70B-V1.0)

粘贴、拖放或点击上传图像（.png、.jpeg、.jpg、.svg、.gif）