added this file

.ipynb_checkpoints/part4-checkpoint.ipynb

@@ -0,0 +1,340 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "aa7a358a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import CamembertTokenizer, CamembertForMaskedLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "c7e39f7f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f07d3dc0c67842c5905d2a8d9bbc0ee8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=810912.0, style=ProgressStyle(descripti…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "bafae4f91f7e490087300d6fcd12ad15",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1395301.0, style=ProgressStyle(descript…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "55b5654c906441d3bba3d48c72a373f2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=508.0, style=ProgressStyle(description_…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "659a9e30adb94f24bd78d87fb4f7706d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=445032417.0, style=ProgressStyle(descri…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "tokenizer = CamembertTokenizer.from_pretrained(\"camembert-base\")\n",
+    "model = CamembertForMaskedLM.from_pretrained(\"camembert-base\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "fff6346c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import notebook_login"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3b8b1722",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Login successful\n",
+      "Your token has been saved to C:\\Users\\1seba/.huggingface/token\n",
+      "\u001b[1m\u001b[31mAuthenticated through git-credential store but this isn't the helper defined on your machine.\n",
+      "You might have to re-authenticate when pushing to the Hugging Face Hub. Run the following command in your terminal in case you want to set this credential helper as the default\n",
+      "\n",
+      "git config --global credential.helper store\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "notebook_login()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e50eaa96",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import TrainingArguments"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "abdb0496",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# training_args = TrainingArguments(\n",
+    "#     \"bert-finetuned-mrpc\", save_strategy=\"epoch\", push_to_hub=True, hub_model_id=\"SebastianS/dummy\"\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "33d7f045",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModelForMaskedLM, AutoTokenizer\n",
+    "checkpoint = \"camembert-base\"\n",
+    "model = AutoModelForMaskedLM.from_pretrained(checkpoint)\n",
+    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7ce0651f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Anaconda\\envs\\AI\\lib\\site-packages\\huggingface_hub\\hf_api.py:723: FutureWarning: `create_repo` now takes `token` as an optional positional argument. Be sure to adapt your code!\n",
+      "  warnings.warn(\n",
+      "Cloning https://huggingface.co/SebastianS/dummy-model into local empty directory.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2dc66be4581641e2992f3fd5821d4147",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Upload file pytorch_model.bin:   0%|          | 32.0k/422M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "To https://huggingface.co/SebastianS/dummy-model\n",
+      "   ca0d412..41a980c  main -> main\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "model.push_to_hub(\"dummy-model\", token=\"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\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ed8312cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import (\n",
+    "    # User management\n",
+    "    login,\n",
+    "    logout,\n",
+    "    whoami,\n",
+    "\n",
+    "    # Repository creation and management\n",
+    "    create_repo,\n",
+    "    delete_repo,\n",
+    "    update_repo_visibility,\n",
+    "\n",
+    "    # And some methods to retrieve/change information about the content\n",
+    "    list_models,\n",
+    "    list_datasets,\n",
+    "    list_metrics,\n",
+    "    list_repo_files,\n",
+    "    upload_file,\n",
+    "    delete_file,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "71af81a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://huggingface.co/SebastianS/dummy-model'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "create_repo(\"dummy-model\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "1d5fd185",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://huggingface.co/SebastianS/dummy-model/blob/main/ch3.ipynb'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "upload_file(\"./ch3.ipynb\", path_in_repo=\"ch3.ipynb\", repo_id=\"SebastianS/dummy-model\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "02a3cc53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import Repository"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5122830e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "repo = Repository(\"../sharing\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06ef92c9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "AI",
+   "language": "python",
+   "name": "ai"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

part4.ipynb

@@ -0,0 +1,350 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "aa7a358a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import CamembertTokenizer, CamembertForMaskedLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "c7e39f7f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f07d3dc0c67842c5905d2a8d9bbc0ee8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=810912.0, style=ProgressStyle(descripti…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "bafae4f91f7e490087300d6fcd12ad15",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1395301.0, style=ProgressStyle(descript…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "55b5654c906441d3bba3d48c72a373f2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=508.0, style=ProgressStyle(description_…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "659a9e30adb94f24bd78d87fb4f7706d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=445032417.0, style=ProgressStyle(descri…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "tokenizer = CamembertTokenizer.from_pretrained(\"camembert-base\")\n",
+    "model = CamembertForMaskedLM.from_pretrained(\"camembert-base\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "fff6346c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import notebook_login"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3b8b1722",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Login successful\n",
+      "Your token has been saved to C:\\Users\\1seba/.huggingface/token\n",
+      "\u001b[1m\u001b[31mAuthenticated through git-credential store but this isn't the helper defined on your machine.\n",
+      "You might have to re-authenticate when pushing to the Hugging Face Hub. Run the following command in your terminal in case you want to set this credential helper as the default\n",
+      "\n",
+      "git config --global credential.helper store\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "notebook_login()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e50eaa96",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import TrainingArguments"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "abdb0496",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# training_args = TrainingArguments(\n",
+    "#     \"bert-finetuned-mrpc\", save_strategy=\"epoch\", push_to_hub=True, hub_model_id=\"SebastianS/dummy\"\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "33d7f045",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModelForMaskedLM, AutoTokenizer\n",
+    "checkpoint = \"camembert-base\"\n",
+    "model = AutoModelForMaskedLM.from_pretrained(checkpoint)\n",
+    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7ce0651f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Anaconda\\envs\\AI\\lib\\site-packages\\huggingface_hub\\hf_api.py:723: FutureWarning: `create_repo` now takes `token` as an optional positional argument. Be sure to adapt your code!\n",
+      "  warnings.warn(\n",
+      "Cloning https://huggingface.co/SebastianS/dummy-model into local empty directory.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2dc66be4581641e2992f3fd5821d4147",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Upload file pytorch_model.bin:   0%|          | 32.0k/422M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "To https://huggingface.co/SebastianS/dummy-model\n",
+      "   ca0d412..41a980c  main -> main\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "model.push_to_hub(\"dummy-model\", token=\"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\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ed8312cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import (\n",
+    "    # User management\n",
+    "    login,\n",
+    "    logout,\n",
+    "    whoami,\n",
+    "\n",
+    "    # Repository creation and management\n",
+    "    create_repo,\n",
+    "    delete_repo,\n",
+    "    update_repo_visibility,\n",
+    "\n",
+    "    # And some methods to retrieve/change information about the content\n",
+    "    list_models,\n",
+    "    list_datasets,\n",
+    "    list_metrics,\n",
+    "    list_repo_files,\n",
+    "    upload_file,\n",
+    "    delete_file,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "71af81a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://huggingface.co/SebastianS/dummy-model'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "create_repo(\"dummy-model\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "1d5fd185",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://huggingface.co/SebastianS/dummy-model/blob/main/ch3.ipynb'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "upload_file(\"./ch3.ipynb\", path_in_repo=\"ch3.ipynb\", repo_id=\"SebastianS/dummy-model\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "02a3cc53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from huggingface_hub import Repository"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5122830e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "repo = Repository(\"../sharing\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "06ef92c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "repo.git_pull()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "574529d9",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "AI",
+   "language": "python",
+   "name": "ai"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}