Upload Sid_GPT_Demo.ipynb with huggingface_hub

Sid_GPT_Demo.ipynb

@@ -0,0 +1,83 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Sid-GPT demo\n",
+    "A 92M-parameter GPT built from scratch that rewrites weak PM resume bullets into quantified, action-led ones.\n",
+    "\n",
+    "Run the cells top to bottom (Runtime \u2192 Run all). The last cell gives you a public link to a small web app."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "!pip -q install torch tokenizers huggingface_hub gradio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "import sys, torch\n",
+    "from huggingface_hub import snapshot_download\n",
+    "path = snapshot_download(\"Sidhartha-Rajput/sid-gpt-resume-llm\")\n",
+    "sys.path.insert(0, path)\n",
+    "from model import GPT\n",
+    "from tokenizers import ByteLevelBPETokenizer\n",
+    "\n",
+    "tok = ByteLevelBPETokenizer(f\"{path}/tokenizer/vocab.json\", f\"{path}/tokenizer/merges.txt\")\n",
+    "ckpt = torch.load(f\"{path}/sft.pt\", map_location=\"cpu\", weights_only=False)\n",
+    "model = GPT(ckpt[\"config\"]); model.load_state_dict(ckpt[\"model\"]); model.eval()\n",
+    "UID, AID, EOT = (tok.token_to_id(t) for t in (\"<|user|>\", \"<|assistant|>\", \"<|endoftext|>\"))\n",
+    "TEMPLATE = \"Turn this into a strong, quantified PM resume bullet:\\n{}\"\n",
+    "\n",
+    "def rewrite(bullet, temperature=0.5, top_k=20, max_new_tokens=70):\n",
+    "    ids = [UID] + tok.encode(TEMPLATE.format(bullet.strip())).ids + [AID]\n",
+    "    with torch.no_grad():\n",
+    "        out = model.generate(torch.tensor([ids]), max_new_tokens=int(max_new_tokens),\n",
+    "                             temperature=float(temperature), top_k=int(top_k))\n",
+    "    new = out[0, len(ids):].tolist()\n",
+    "    if EOT in new: new = new[:new.index(EOT)]\n",
+    "    return tok.decode(new).strip()\n",
+    "\n",
+    "print(rewrite(\"Responsible for managing the product roadmap for the mobile app.\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {},
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "import gradio as gr\n",
+    "gr.Interface(\n",
+    "    fn=rewrite,\n",
+    "    inputs=[gr.Textbox(label=\"Your resume bullet\", lines=3),\n",
+    "            gr.Slider(0.2, 1.2, value=0.5, label=\"Temperature\"),\n",
+    "            gr.Slider(1, 100, value=20, step=1, label=\"Top-k\"),\n",
+    "            gr.Slider(20, 120, value=70, step=5, label=\"Max new tokens\")],\n",
+    "    outputs=gr.Textbox(label=\"Sid-GPT rewrite\", lines=4),\n",
+    "    title=\"Sid-GPT: PM resume bullet rewriter\",\n",
+    ").launch(share=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}