Upload 9 files

GPT2_Greentext.ipynb

@@ -0,0 +1,109 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU",
+    "gpuClass": "standard"
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "u7RAqjzj4ylm"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install happytransformer"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from happytransformer import HappyGeneration\n",
+        "\n",
+        "happy_gen = HappyGeneration(\"GPT2\", \"gpt2-medium\")"
+      ],
+      "metadata": {
+        "id": "4V9hd8bQ41HD"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!wget https://huggingface.co/datasets/DarwinAnim8or/greentext/resolve/main/greentexts.txt"
+      ],
+      "metadata": {
+        "id": "hz3fzo5W9ppf"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from happytransformer import GENTrainArgs \n",
+        "\n",
+        "args = GENTrainArgs(learning_rate =1e-5, num_train_epochs = 15)\n",
+        "happy_gen.train(\"greentexts.txt\", args=args)"
+      ],
+      "metadata": {
+        "id": "Yl4wNVvK5Bex"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from happytransformer import GENSettings\n",
+        "args_top_k = GENSettings(no_repeat_ngram_size=3, do_sample=True, top_k=80, temperature=0.8, max_length=150, early_stopping=False)"
+      ],
+      "metadata": {
+        "id": "LXi7hXFtBLpN"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "result = happy_gen.generate_text(\"\"\"Write a greentext from 4chan.org. The story should be like a bullet-point list using > as the start of each line. Most greentexts are humorous or absurd in nature. Most greentexts have a twist near the end.\n",
+        ">be me\n",
+        ">\"\"\", args=args_top_k)\n",
+        "\n",
+        "#print(result)\n",
+        "print(result.text)"
+      ],
+      "metadata": {
+        "id": "ih4KihPy_U_h"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#To save the model, run this cell.\n",
+        "happy_gen.save(\"gpt2-greentext-epoch-15/\")"
+      ],
+      "metadata": {
+        "id": "LFUPtXAo_dTz"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": "4.26.0",
+  "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": "4.26.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65421c874ba12c51099f79057af65240fdcde9b11a65d67e86807d8d429be02
+size 1444569373

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2-medium",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}