huggingface_hub/upload_hf_model.ipynb (432 lines of code) (raw):

{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "Upload_hf_model.ipynb", "provenance": [], "collapsed_sections": [], "machine_shape": "hm", "include_colab_link": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "<a href=\"https://colab.research.google.com/github/huggingface/notebooks/blob/upload_hf_model/huggingface_hub/upload_hf_model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "mpyOZpyNbe4s", "outputId": "f0ebe61d-f355-4d32-8f8d-627856add2c0" }, "source": [ "!pip install transformers\n", "!sudo apt-get install git-lfs" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Requirement already satisfied: transformers in /usr/local/lib/python3.6/dist-packages (4.1.1)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from transformers) (1.19.4)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from transformers) (2.23.0)\n", "Requirement already satisfied: tokenizers==0.9.4 in /usr/local/lib/python3.6/dist-packages (from transformers) (0.9.4)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.6/dist-packages (from transformers) (3.0.12)\n", "Requirement already satisfied: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from transformers) (0.8)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers) (2019.12.20)\n", "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from transformers) (4.41.1)\n", "Requirement already satisfied: sacremoses in /usr/local/lib/python3.6/dist-packages (from transformers) (0.0.43)\n", "Requirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from transformers) (20.8)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2020.12.5)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (1.24.3)\n", "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2.10)\n", "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (3.0.4)\n", "Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.15.0)\n", "Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.0.0)\n", "Requirement already satisfied: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (7.1.2)\n", "Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from packaging->transformers) (2.4.7)\n", "Reading package lists... Done\n", "Building dependency tree \n", "Reading state information... Done\n", "git-lfs is already the newest version (2.3.4-1).\n", "0 upgraded, 0 newly installed, 0 to remove and 15 not upgraded.\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "XxYs3FFjfZgg" }, "source": [ "!git config --global user.email \"julien@huggingface.co\"\n", "!git config --global user.name \"Julien Chaumond\"" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "MEixzjPibn_t" }, "source": [ "!transformers-cli login" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "rirFL2oEcBxo", "outputId": "e45a2a89-45a0-427e-baff-c18e07aa1278" }, "source": [ "!pwd" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "/content\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "dxKVjZBfcKdr", "outputId": "2da79381-12ce-486c-c7d8-96e54ea9ed23" }, "source": [ "!transformers-cli repo create policy-distilbert-7d" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "2020-12-26 10:02:28.904892: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1\n", "\u001b[90mgit version 2.17.1\u001b[0m\n", "Error: unknown flag: --version\n", "\n", "\u001b[90mSorry, no usage text found for \"git-lfs\"\u001b[0m\n", "\n", "You are about to create \u001b[1mjulien-c/policy-distilbert-7d\u001b[0m\n", "Proceed? [Y/n] Y\n", "\n", "Your repo now lives at:\n", " \u001b[1mhttps://huggingface.co/julien-c/policy-distilbert-7d\u001b[0m\n", "\n", "You can clone it locally with the command below, and commit/push as usual.\n", "\n", " git clone https://huggingface.co/julien-c/policy-distilbert-7d\n", "\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "5R6NQVkLcN4v", "outputId": "b767deb5-4966-4e82-853f-6d65300d4c5c" }, "source": [ "!git clone https://julien-c:...token...@huggingface.co/julien-c/policy-distilbert-7d" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Cloning into 'policy-distilbert-7d'...\n", "remote: Enumerating objects: 3, done.\u001b[K\n", "remote: Counting objects: 100% (3/3), done.\u001b[K\n", "remote: Compressing objects: 100% (2/2), done.\u001b[K\n", "remote: Total 3 (delta 0), reused 0 (delta 0)\u001b[K\n", "Unpacking objects: 100% (3/3), done.\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "iS_wSC-IcklY", "outputId": "0caf0b61-58fc-4892-bee3-6ea30fb6531f" }, "source": [ "!ls -al" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "total 20\n", "drwxr-xr-x 1 root root 4096 Dec 26 10:03 .\n", "drwxr-xr-x 1 root root 4096 Dec 26 09:42 ..\n", "drwxr-xr-x 1 root root 4096 Dec 21 17:29 .config\n", "drwxr-xr-x 3 root root 4096 Dec 26 10:03 policy-distilbert-7d\n", "drwxr-xr-x 1 root root 4096 Dec 21 17:29 sample_data\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "1zYuepDccmgH", "outputId": "07af3a37-56c0-4215-b8d6-03ff89944f79" }, "source": [ "%cd policy-distilbert-7d" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "/content/policy-distilbert-7d\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Dm8Ffkpmc9ui", "outputId": "5024777a-ebdd-4f70-e67b-9c0cb6490be4" }, "source": [ "!wget https://huggingface.co/distilbert-base-uncased/resolve/main/config.json\n", "!wget https://huggingface.co/distilbert-base-uncased/resolve/main/pytorch_model.bin" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "--2020-12-26 10:03:55-- https://huggingface.co/distilbert-base-uncased/resolve/main/config.json\n", "Resolving huggingface.co (huggingface.co)... 34.201.172.85\n", "Connecting to huggingface.co (huggingface.co)|34.201.172.85|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 442 [application/json]\n", "Saving to: ‘config.json’\n", "\n", "\rconfig.json 0%[ ] 0 --.-KB/s \rconfig.json 100%[===================>] 442 --.-KB/s in 0s \n", "\n", "2020-12-26 10:03:55 (56.7 MB/s) - ‘config.json’ saved [442/442]\n", "\n", "--2020-12-26 10:03:55-- https://huggingface.co/distilbert-base-uncased/resolve/main/pytorch_model.bin\n", "Resolving huggingface.co (huggingface.co)... 34.201.172.85\n", "Connecting to huggingface.co (huggingface.co)|34.201.172.85|:443... connected.\n", "HTTP request sent, awaiting response... 302 Found\n", "Location: https://cdn-lfs.huggingface.co/distilbert-base-uncased/e60d71610916da4787c5513c81bc026d415708528295502fb3e1a6fe1485ea7c [following]\n", "--2020-12-26 10:03:55-- https://cdn-lfs.huggingface.co/distilbert-base-uncased/e60d71610916da4787c5513c81bc026d415708528295502fb3e1a6fe1485ea7c\n", "Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 13.226.49.106, 13.226.49.46, 13.226.49.103, ...\n", "Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|13.226.49.106|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 267967963 (256M) [application/macbinary]\n", "Saving to: ‘pytorch_model.bin’\n", "\n", "pytorch_model.bin 100%[===================>] 255.55M 87.1MB/s in 2.9s \n", "\n", "2020-12-26 10:03:58 (87.1 MB/s) - ‘pytorch_model.bin’ saved [267967963/267967963]\n", "\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-y-GHzOigVjC", "outputId": "febf16e7-2cda-4730-e44e-b354e9c2308a" }, "source": [ "!git lfs install" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Updated git hooks.\n", "Git LFS initialized.\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "4GEDLShhdAe8" }, "source": [ "!git add ." ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "peUV0eaYdOxn", "outputId": "7f0ad732-3786-4f11-be2e-c16bddfbbc8f" }, "source": [ "!git commit -m \"from Google Colab\"" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "[main 41a7c98] from Google Colab\n", " 2 files changed, 24 insertions(+)\n", " create mode 100644 config.json\n", " create mode 100644 pytorch_model.bin\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "FbeYiBCAdbAt", "outputId": "6647c7f8-5d04-4555-9a92-c59e3e9fad87" }, "source": [ "!git log" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "\u001b[33mcommit 41a7c98f1285a7e5ef19095dab11f0ac71ac1406\u001b[m\u001b[33m (\u001b[m\u001b[1;36mHEAD -> \u001b[m\u001b[1;32mmain\u001b[m\u001b[33m)\u001b[m\n", "Author: Julien Chaumond <julien@huggingface.co>\n", "Date: Sat Dec 26 10:04:20 2020 +0000\n", "\n", " from Google Colab\n", "\n", "\u001b[33mcommit 4630180ab4844ecc97c7f187c3d5bc54a568fac0\u001b[m\u001b[33m (\u001b[m\u001b[1;31morigin/main\u001b[m\u001b[33m, \u001b[m\u001b[1;31morigin/HEAD\u001b[m\u001b[33m)\u001b[m\n", "Author: system <system@huggingface.co>\n", "Date: Sat Dec 26 10:02:45 2020 +0000\n", "\n", " initial commit\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "y08-nstXdqPH", "outputId": "d383d262-d6da-49c3-e7e5-7fc65255996a" }, "source": [ "!git push" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Git LFS: (1 of 1 files) 255.55 MB / 255.55 MB\n", "Counting objects: 4, done.\n", "Delta compression using up to 4 threads.\n", "Compressing objects: 100% (4/4), done.\n", "Writing objects: 100% (4/4), 712 bytes | 712.00 KiB/s, done.\n", "Total 4 (delta 0), reused 0 (delta 0)\n", "To https://huggingface.co/julien-c/policy-distilbert-7d\n", " 4630180..41a7c98 main -> main\n" ], "name": "stdout" } ] }, { "cell_type": "markdown", "metadata": { "id": "Pp0W8O1gggpZ" }, "source": [ "## Check out resulting commit: https://huggingface.co/julien-c/policy-distilbert-7d/commit/41a7c98f1285a7e5ef19095dab11f0ac71ac1406" ] }, { "cell_type": "code", "metadata": { "id": "cBQPu2kjgplw" }, "source": [ "" ], "execution_count": null, "outputs": [] } ] }