Inkling：我们的开放权重模型

Inkling：我们的开放权重模型（来源）Mira Murati 的 Thinking Machines Lab 刚刚发布了他们的第一个开放权重模型。Inkling 是“一个混合专家（MoE）Transformer，总参数量 975B，活跃参数 41B”——采用 Apache-2.0 许可的多模态模型，在 45 万亿 token 的文本、图像、音频和视频数据上训练。

他们还预告了 Inkling-Small，一款 276B（12B 活跃参数）的模型，但该模型仍在测试中，权重将在“这项工作完成后”发布。

模型卡比我对美国 AI 实验室的期望要简短得多。它链接到更简短的训练数据文档，其中几乎没有提供有趣的信息——以下两段话最能概括：

Thinking Machines Lab 用于开发其 AI 服务的数据集中包含公共领域的内容，以及可能受知识产权保护的内容。

Thinking Machines Lab 的服务是使用从开放互联网和公共可访问数据仓库中获取的公开内容开发的。某些数据集还从第三方获得。

据 Thinking Machines 自己承认，这并不是一个前沿模型。相反，它旨在作为使用他们自己的 Tinker 训练平台 进行微调的强大基础模型：

Inkling 并不是当今可用的最强模型，无论是开源还是闭源。相反，多种特性的结合使其成为一个适合定制的开放权重基础模型：多模态能力、高效思考，以及在 Tinker 上可进行微调。

这次发布有许多值得赞赏之处。它采用 Apache-2.0 许可，看起来与中国的开放权重模型具有竞争力——很高兴看到美国开放权重生态系统中新增一个有活力的竞争者，加入 NVIDIA Nemotron 和 Gemma 4 的行列。

下面是我通过 Thinking Machines API 使用这个 curl 命令生成的、尝试绘制骑自行车的鹈鹕 SVG：

curl "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1/chat/completions" \
  -H "Authorization: Bearer $TINKER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/Inkling",
    "messages": [
      {"role": "user", "content": "Generate an SVG of a pelican riding a bicycle"}
    ],
    "stream": false
  }'

完整响应见此。

由于它是一个多模态模型，我让它描述自己的图像（在渲染成 JPEG 之后），发送了以下 JSON：

{
  "model": "thinkingmachines/Inkling",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,$BASE_64_JPEG"}},
      {"type": "text", "text": "Describe this image in detail"},
    ],
  }],
  "stream": false
}

这是完整响应。它认为自己画了一只“鹳或海鸥”：

这是一幅欢快的扁平矢量卡通插画，描绘了一只白色的鸟骑着自行车穿过绿色风景。

鸟： 中心形象是一只风格化的白鸟——类似鹳或海鸥——身体丰满圆润。它有长长的、突出的橙色鸟喙，微微张开，露出一条黑色的嘴巴线条。眼睛小而黑，带着微小的白色高光。鸟的翅膀和尾羽为黑色，边缘白色，细长的橙色腿末端是黑色的脚，踩在自行车的橙色踏板上。

自行车： 自行车有一个简单的黑色车架，配有两个大轮子，有黑色轮胎、灰色内圈和交叉排列的黑色辐条。车把是黑色的，明亮的橙色踏板连接在黑色曲柄上。鸟身后面可以看到一个白色车座。

场景： 场景背景是晴朗的淡蓝色天空。有两朵蓬松的白云——一朵在左边，较小的在鸟头附近的右边。右上角有一个明亮的实心黄色太阳。底部是起伏的绿色山丘，平滑弯曲的顶部边缘，自行车停在那里。

整体风格俏皮、简洁、多彩，线条干净，气氛明亮、阳光。

Inkling: Our open-weights model (via) Mira Murati's Thinking Machines Lab just released their first open-weights model. Inkling is "a Mixture-of-Experts transformer with 975B total parameters, 41B active" - an Apache-2.0 licensed multimodal model trained on 45 trillion tokens of text, images, audio and video.

They're also promising Inkling-Small, a 276B (12B active) model, but that's still being tested and the weights will be released "once that work is complete".

The model card is much shorter than I've come to expect from US AI labs. It links to even shorter Training Data Documentation with almost nothing of interest in it - it's best summarized by these two paragraphs:

The datasets Thinking Machines Lab uses to develop its AI services includes content that is in the public domain as well as content that may be subject to intellectual property protection.

Thinking Machines Lab’s services were developed using publicly available content obtained from the open internet and publicly accessible data repositories. Certain datasets were also obtained from third parties.

By Thinking Machines' own admission, this is not a frontier model. It's instead intended as a strong base model for fine-tuning using their own Tinker training platform:

Inkling is not the strongest overall model available today, open or closed. Instead, a combination of qualities makes it a good open-weights base for customization: multimodal capabilities, efficient thinking, and availability on Tinker for fine-tuning.

There's a lot to like about this release. It's Apache-2.0 licensed, and looks competitive with the open weight models coming out of China - it's good to see the US open weights ecosystem gain a new viable contender to join NVIDIA Nemotron and Gemma 4.

Here's its attempt at an SVG pelican riding a bicycle, which I generated using this curl command against the Thinking Machines API:

curl "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1/chat/completions" \
  -H "Authorization: Bearer $TINKER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/Inkling",
    "messages": [
      {"role": "user", "content": "Generate an SVG of a pelican riding a bicycle"}
    ],
    "stream": false
  }'

Full response here.

Since it's a multi-modal model I had it describe its own image (after I rendered it to a JPEG) by sending this JSON:

{
  "model": "thinkingmachines/Inkling",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,$BASE_64_JPEG"}},
      {"type": "text", "text": "Describe this image in detail"},
    ],
  }],
  "stream": false
}

Here's the full response. It thought it had drawn a "stork or seagull":

This is a cheerful, flat-vector cartoon illustration featuring a white bird riding a bicycle across a green landscape.

The Bird: The central figure is a stylized white bird—resembling a stork or seagull—with a plump, rounded body. It has a long, prominent orange beak that is slightly open, revealing a black line for the mouth. Its eye is small and black with a tiny white highlight. The bird has black wing and tail feathers with white edges, and thin orange legs ending in black feet that rest on the bicycle's orange pedals.

The Bicycle: The bike has a simple black frame with two large wheels featuring black tires, gray inner rims, and black spokes arranged in a cross pattern. The handlebars are black, and there are bright orange pedals attached to a black crank. A white seat is visible behind the bird's body.

The Setting: The scene is set against a clear, light blue sky. There are two fluffy white clouds—one on the left side and a smaller one near the bird's head on the right. A bright, solid yellow sun shines in the upper right corner. At the bottom, there are rolling green hills with a smooth, curved top edge where the bicycle rests.

The overall style is playful, simple, and colorful, with clean lines and a bright, sunny atmosphere.