mirror of
https://github.com/deepset-ai/haystack.git
synced 2026-01-06 03:57:19 +00:00
Make use_gpu=True the default in tutorials (#692)
* enable gpu args in tutorials * add info box for gpu runtime on colab
This commit is contained in:
Malte Pietsch
GitHub
parent
b752da1cd5
commit
94b7345505
@ -16,10 +16,39 @@
|
||||
"In this tutorial we will work on a slightly different domain: \"Game of Thrones\". \n",
|
||||
"\n",
|
||||
"Let's see how we can use a bunch of Wikipedia articles to answer a variety of questions about the \n",
|
||||
"marvellous seven kingdoms... \n",
|
||||
"\n"
|
||||
"marvellous seven kingdoms... \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Prepare environment\n",
|
||||
"\n",
|
||||
"#### Colab: Enable the GPU runtime\n",
|
||||
"Make sure you enable the GPU runtime to experience decent speed in this tutorial.\n",
|
||||
"**Runtime -> Change Runtime type -> Hardware accelerator -> GPU**\n",
|
||||
"\n",
|
||||
"<img src=\"https://raw.githubusercontent.com/deepset-ai/haystack/master/docs/_src/img/colab_gpu_runtime.jpg\">"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make sure you have a GPU running\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@ -306,7 +335,7 @@
|
||||
"# Load a local model or any of the QA models on\n",
|
||||
"# Hugging Face's model hub (https://huggingface.co/models)\n",
|
||||
"\n",
|
||||
"reader = FARMReader(model_name_or_path=\"deepset/roberta-base-squad2\", use_gpu=False)"
|
||||
"reader = FARMReader(model_name_or_path=\"deepset/roberta-base-squad2\", use_gpu=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@ -128,7 +128,7 @@ retriever = ElasticsearchRetriever(document_store=document_store)
|
||||
|
||||
# Load a local model or any of the QA models on
|
||||
# Hugging Face's model hub (https://huggingface.co/models)
|
||||
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
|
||||
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)
|
||||
|
||||
# #### TransformersReader
|
||||
|
||||
|
||||
@ -15,6 +15,36 @@
|
||||
"This tutorial shows you how to fine-tune a pretrained model on your own dataset."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Prepare environment\n",
|
||||
"\n",
|
||||
"#### Colab: Enable the GPU runtime\n",
|
||||
"Make sure you enable the GPU runtime to experience decent speed in this tutorial.\n",
|
||||
"**Runtime -> Change Runtime type -> Hardware accelerator -> GPU**\n",
|
||||
"\n",
|
||||
"<img src=\"https://raw.githubusercontent.com/deepset-ai/haystack/master/docs/_src/img/colab_gpu_runtime.jpg\">"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make sure you have a GPU running\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
|
||||
@ -15,6 +15,36 @@
|
||||
"If you are interested in more feature-rich Elasticsearch, then please refer to the Tutorial 1. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Prepare environment\n",
|
||||
"\n",
|
||||
"#### Colab: Enable the GPU runtime\n",
|
||||
"Make sure you enable the GPU runtime to experience decent speed in this tutorial.\n",
|
||||
"**Runtime -> Change Runtime type -> Hardware accelerator -> GPU**\n",
|
||||
"\n",
|
||||
"<img src=\"https://raw.githubusercontent.com/deepset-ai/haystack/master/docs/_src/img/colab_gpu_runtime.jpg\">"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make sure you have a GPU running\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@ -224,7 +254,7 @@
|
||||
"# Load a local model or any of the QA models on\n",
|
||||
"# Hugging Face's model hub (https://huggingface.co/models)\n",
|
||||
"\n",
|
||||
"reader = FARMReader(model_name_or_path=\"deepset/roberta-base-squad2\", use_gpu=False)"
|
||||
"reader = FARMReader(model_name_or_path=\"deepset/roberta-base-squad2\", use_gpu=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@ -83,7 +83,7 @@ retriever = TfidfRetriever(document_store=document_store)
|
||||
#
|
||||
# Load a local model or any of the QA models on
|
||||
# Hugging Face's model hub (https://huggingface.co/models)
|
||||
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
|
||||
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)
|
||||
|
||||
|
||||
# #### TransformersReader
|
||||
|
||||
@ -20,9 +20,39 @@
|
||||
"\n",
|
||||
"- Generalizability: We can only answer questions that are similar to existing ones in FAQ\n",
|
||||
"\n",
|
||||
"In some use cases, a combination of extractive QA and FAQ-style can also be an interesting option.\n"
|
||||
"In some use cases, a combination of extractive QA and FAQ-style can also be an interesting option."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Prepare environment\n",
|
||||
"\n",
|
||||
"#### Colab: Enable the GPU runtime\n",
|
||||
"Make sure you enable the GPU runtime to experience decent speed in this tutorial.\n",
|
||||
"**Runtime -> Change Runtime type -> Hardware accelerator -> GPU**\n",
|
||||
"\n",
|
||||
"<img src=\"https://raw.githubusercontent.com/deepset-ai/haystack/master/docs/_src/img/colab_gpu_runtime.jpg\">"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make sure you have a GPU running\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
|
||||
@ -18,6 +18,36 @@
|
||||
"To be able to make a statement about the performance of a question-answering system, it is important to evalute it. Furthermore, evaluation allows to determine which parts of the system can be improved."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Prepare environment\n",
|
||||
"\n",
|
||||
"#### Colab: Enable the GPU runtime\n",
|
||||
"Make sure you enable the GPU runtime to experience decent speed in this tutorial.\n",
|
||||
"**Runtime -> Change Runtime type -> Hardware accelerator -> GPU**\n",
|
||||
"\n",
|
||||
"<img src=\"https://raw.githubusercontent.com/deepset-ai/haystack/master/docs/_src/img/colab_gpu_runtime.jpg\">"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make sure you have a GPU running\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
|
||||
@ -15,6 +15,36 @@
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Prepare environment\n",
|
||||
"\n",
|
||||
"#### Colab: Enable the GPU runtime\n",
|
||||
"Make sure you enable the GPU runtime to experience decent speed in this tutorial.\n",
|
||||
"**Runtime -> Change Runtime type -> Hardware accelerator -> GPU**\n",
|
||||
"\n",
|
||||
"<img src=\"https://raw.githubusercontent.com/deepset-ai/haystack/master/docs/_src/img/colab_gpu_runtime.jpg\">"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Make sure you have a GPU running\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
@ -155,14 +185,14 @@
|
||||
" document_store=document_store,\n",
|
||||
" query_embedding_model=\"facebook/dpr-question_encoder-single-nq-base\",\n",
|
||||
" passage_embedding_model=\"facebook/dpr-ctx_encoder-single-nq-base\",\n",
|
||||
" use_gpu=False,\n",
|
||||
" use_gpu=True,\n",
|
||||
" embed_title=True,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Initialize RAG Generator\n",
|
||||
"generator = RAGenerator(\n",
|
||||
" model_name_or_path=\"facebook/rag-token-nq\",\n",
|
||||
" use_gpu=False,\n",
|
||||
" use_gpu=True,\n",
|
||||
" top_k_answers=1,\n",
|
||||
" max_length=200,\n",
|
||||
" min_length=2,\n",
|
||||
|
||||
@ -48,14 +48,14 @@ retriever = DensePassageRetriever(
|
||||
document_store=document_store,
|
||||
query_embedding_model="facebook/dpr-question_encoder-single-nq-base",
|
||||
passage_embedding_model="facebook/dpr-ctx_encoder-single-nq-base",
|
||||
use_gpu=False,
|
||||
use_gpu=True,
|
||||
embed_title=True,
|
||||
)
|
||||
|
||||
# Initialize RAG Generator
|
||||
generator = RAGenerator(
|
||||
model_name_or_path="facebook/rag-token-nq",
|
||||
use_gpu=False,
|
||||
use_gpu=True,
|
||||
top_k_answers=1,
|
||||
max_length=200,
|
||||
min_length=2,
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user