Upload 3 files

Gpt2_LLM_app.ipynb

@@ -0,0 +1,201 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Import the required library\n",
+        "from transformers import pipeline\n",
+        "\n",
+        "# Define the task and model\n",
+        "task = \"text-generation\"\n",
+        "model_name = \"gpt2\"\n",
+        "\n",
+        "# Define the input text, maximum output length, and the number of return sequences\n",
+        "input_text = \"he draw to the town \"\n",
+        "max_output_length = 50\n",
+        "num_of_return_sequences = 1\n",
+        "\n",
+        "# Initialize the text generation pipeline\n",
+        "text_generator = pipeline(\n",
+        "    task,\n",
+        "    model=model_name\n",
+        ")\n",
+        "\n",
+        "# Generate text sequences\n",
+        "generated_texts = text_generator(\n",
+        "    input_text,\n",
+        "    max_length=max_output_length,\n",
+        "    num_return_sequences=num_of_return_sequences\n",
+        ")\n",
+        "\n",
+        "# Print the generated text sequences\n",
+        "for i, text in enumerate(generated_texts):\n",
+        "    print(f\"Generated Text {i+1}: {text['generated_text']}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "0rNsuHRYznUQ",
+        "outputId": "dae8e691-a1f0-4d3a-c521-086522ef9e9d"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.\n",
+            "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Generated Text 1: he draw to the town Ṣuṣṭṭhi, the wind was blowing gently in this direction towards the east, and so the wind was as much as the wind of a mountain. Ṣuṣ�\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Print the generated text sequences\n",
+        "for i, text in enumerate(generated_texts):\n",
+        "    print(f\"Generated Text {i+1}: {text['generated_text']}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wZ6DmKrhsLpC",
+        "outputId": "ce00c00d-b839-49f4-bfc2-59028be6a057"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Generated Text 1: he draw to the town Ṣuṣṭṭhi, the wind was blowing gently in this direction towards the east, and so the wind was as much as the wind of a mountain. Ṣuṣ�\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Print the generated text sequences\n",
+        "for i, text in enumerate(generated_texts):\n",
+        "  print(f\"Generated Text {1}: {text['generated_text']}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "2AdczanhsfUz",
+        "outputId": "9bf873ae-fae0-495a-b5c5-ee890fcc044c"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Generated Text 1: he draw to the town Ṣuṣṭṭhi, the wind was blowing gently in this direction towards the east, and so the wind was as much as the wind of a mountain. Ṣuṣ�\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "generated_texts"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "JZEbsQthsuFZ",
+        "outputId": "3e047f46-fd3e-492a-c5a0-723fdda985cd"
+      },
+      "execution_count": 10,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "[{'generated_text': 'he draw to the town Ṣuṣṭṭhi, the wind was blowing gently in this direction towards the east, and so the wind was as much as the wind of a mountain. Ṣuṣ�'}]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 10
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from transformers import GPT2LMHeadModel, GPT2Tokenizer\n",
+        "\n",
+        "# Define the model and tokenizer\n",
+        "model_name = \"gpt2\"\n",
+        "model = GPT2LMHeadModel.from_pretrained(model_name)\n",
+        "tokenizer = GPT2Tokenizer.from_pretrained(model_name)\n",
+        "\n",
+        "# Save the model and tokenizer\n",
+        "model.save_pretrained(\"model-gpt2-t2t\")\n",
+        "tokenizer.save_pretrained(\"tokenizer-gpt2-t2t\")\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "V0TTg8u0tJOK",
+        "outputId": "aba3223e-d603-486d-daed-2c61f667fd65"
+      },
+      "execution_count": 12,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "('tokenizer-gpt2-t2t/tokenizer_config.json',\n",
+              " 'tokenizer-gpt2-t2t/special_tokens_map.json',\n",
+              " 'tokenizer-gpt2-t2t/vocab.json',\n",
+              " 'tokenizer-gpt2-t2t/merges.txt',\n",
+              " 'tokenizer-gpt2-t2t/added_tokens.json')"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 12
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "g-Scy6tvt_RB"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.2"
+}