nemotron-3-nano

383.1K 下载更新于 3 周前

Nemotron-3-Nano 是高效、开放且智能的智能体模型新标准，现已更新为 4B 参数模型。

工具思考云 4b 30b

ollama run nemotron-3-nano

curl https://:11434/api/chat \
  -d '{
    "model": "nemotron-3-nano",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='nemotron-3-nano',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'nemotron-3-nano',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

应用

Claude Code

Claude 代码 ollama launch claude --model nemotron-3-nano

Codex

Codex ollama launch codex --model nemotron-3-nano

OpenCode

OpenCode ollama launch opencode --model nemotron-3-nano

OpenClaw

OpenClaw ollama launch openclaw --model nemotron-3-nano

模型

查看全部 →

名称

9 个模型

大小

上下文

输入

nemotron-3-nano:latest

24GB · 1M 上下文窗口 · 文本 · 3 个月前

nemotron-3-nano:latest

24GB

1M

文本

nemotron-3-nano:4b

2.8GB · 256K 上下文窗口 · 文本 · 3 周前

nemotron-3-nano:4b

2.8GB

256K

文本

nemotron-3-nano:30b

24GB · 1M 上下文窗口 · 文本 · 3 个月前

nemotron-3-nano:30b 最新

24GB

1M

文本

nemotron-3-nano:30b-cloud

1M 上下文窗口 · 文本 · 3 个月前

nemotron-3-nano:30b-cloud

-

1M

文本

自述文件

Nemotron-3-Nano

Nemotron 3 Nano 4B

ollama run nemotron-3-nano:4b

Nemotron 3 Nano 30B

ollama run nemotron-3-nano:30b

Ollama 的云服务

ollama run nemotron-3-nano:30b-cloud

什么是 Nemotron？

NVIDIA Nemotron™ 是一系列具有开放权重、训练数据和配方的开放模型，为构建专门的 AI 代理提供领先的效率和准确性。

Nemotron 3 Nano 是 NVIDIA 从头开始训练的大型语言模型 (LLM)，专为推理和非推理任务设计为统一模型。它首先生成推理轨迹，然后得出最终响应来响应用户的查询和任务。模型的推理能力可以通过聊天模板中的一个标志进行配置。如果用户希望模型在没有中间推理轨迹的情况下提供最终答案，可以将其配置为这样做，尽管对于需要推理的更难提示，准确性会略有下降。相反，允许模型首先生成推理轨迹通常会产生更高质量的查询和任务的最终解决方案。

该模型采用混合专家混合 (MoE) 架构，由 23 个 Mamba-2 和 MoE 层以及 6 个注意力层组成。每个 MoE 层包括 128 个专家和一个共享专家，每个令牌激活 6 个专家。该模型具有 3.5B 个活动参数和 30B 个总参数。

支持的语言包括：英语、德语、西班牙语、法语、意大利语和日语。使用 Qwen 改进。

许可/使用条款

管理条款：本模型的使用受 NVIDIA Open Model License Agreement 的约束。

# Nemotron-3-Nano

**Nemotron 3 Nano 4B**

```
ollama run nemotron-3-nano:4b
```

**Nemotron 3 Nano 30B**

```
ollama run nemotron-3-nano:30b
```

**Ollama's Cloud**

```
ollama run nemotron-3-nano:30b-cloud
```

### What is Nemotron?

NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents.

Nemotron 3 Nano is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks.

The model employs a hybrid Mixture-of-Experts (MoE) architecture, consisting of 23 Mamba-2 and MoE layers, along with 6 Attention layers. Each MoE layer includes 128 experts plus 1 shared expert, with 6 experts activated per token. The model has 3.5B active parameters and 30B parameters in total.

The supported languages include: English, German, Spanish, French, Italian, and Japanese. Improved using Qwen.

## License/Terms of Use

Governing Terms: Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).

粘贴、拖放或单击以上传图像（.png、.jpeg、.jpg、.svg、.gif）