File size: 1,747 Bytes
e90c14c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "machine_shape": "hm",
      "gpuType": "T4",
      "provenance": []
    },
    "accelerator": "GPU",
    "kaggle": {
      "accelerator": "gpu"
    },
    "language_info": {
      "name": "python"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!pip install -U transformers"
      ],
      "metadata": {
        "id": "4LXugJ1wUN5o"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Local Inference on GPU\n",
        "Model page: https://huggingface.co/vikhyatk/moondream2\n",
        "\n",
        "⚠️ If the generated code snippets do not work, please open an issue on either the [model repo](https://huggingface.co/vikhyatk/moondream2)\n",
        "\t\t\tand/or on [huggingface.js](https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/model-libraries-snippets.ts) 🙏"
      ],
      "metadata": {
        "id": "t490XrsVUN5q"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
        "\n",
        "tokenizer = AutoTokenizer.from_pretrained(\"vikhyatk/moondream2\")\n",
        "model = AutoModelForCausalLM.from_pretrained(\n",
        "    \"vikhyatk/moondream2\",\n",
        "    revision=\"2025-06-21\",\n",
        "    trust_remote_code=True,\n",
        "    device_map={\"\": \"cuda\"}\n",
        ")"
      ],
      "metadata": {
        "id": "6aWNuxB8UN5s"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}