|
|
|
|
Quelle classifier.ipynb Sprache: unbekannt
|
|
Spracherkennung für: .ipynb vermutete Sprache: SPS {SPS[36] Python[27] R[18]} [Methode: maximale Elemente, drei Dimensionen]
{
"cells": [
{
"cell_type": "markdown",
"id": "0f47fc4b-7cdc-48ce-b42c-e0b73d902ece",
"metadata": {},
"source": [
"# Train a classifier with Mistral 7B"
]
},
{
"cell_type": "markdown",
"id": "bfd6bdfb-c8cc-4fb6-8969-153a97dfb576",
"metadata": {},
"source": [
"In this tutorial, we will see how we can leverage Mistral 7B to train a classifier. We need:\n",
"- The mistral codebase: `https://github.com/mistralai/mistral-inference`\n",
"- The pretrained model and its tokenizer: `https://docs.mistral.ai/llm/mistral-v0.1`\n",
"- A dataset to train our classifier\n",
"\n",
"We will train and evaluate the classifier on `Symptom2Disease`, a public classification dataset from Kaggle provided in a CSV format: https://www.kaggle.com/datasets/niyarrbarman/symptom2disease/"
]
},
{
"cell_type": "markdown",
"id": "225f88da-96ab-4262-88f8-8f1d6d5224bd",
"metadata": {},
"source": [
"## Set paths"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ebe4bc9b-d0f7-42a6-9e41-bb3d042e0e07",
"metadata": {},
"outputs": [],
"source": [
"from pathlib import Path\n",
"\n",
"code_path = \"/codebase_path/mistral-inference\ " # codebase\n",
"data_path = Path(\"/dataset_path/Symptom2Disease.csv\ ") # dataset downloaded from Kaggle\n",
"model_path = Path(\"/model_path/\ ") # model and tokenizer location"
]
},
{
"cell_type": "markdown",
"id": "3fcc420b-2ac7-42e1-a3b1-8a80f87ccc10",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5e8227fe-d2fb-4a2f-a136-96ee2d32287f",
"metadata": {},
"outputs": [],
"source": [
"import csv\n",
"import tqdm\n",
"import torch\n",
"import numpy as np\n",
"\n",
"import sys\n",
"sys.path.append(code_path) # append the path where mistral-inference was cloned\n",
"\n",
"from mistral.model import Transformer\n",
"from mistral_common.tokens.tokenizers.mistral import MistralTokenizer"
]
},
{
"cell_type": "markdown",
"id": "3b9c8408-1bc1-4e79-8b6d-391e07d78eb4",
"metadata": {},
"source": [
"## Load the model and tokenizer"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "806ff308-5909-46f7-b10e-8b1f1c7b7edc",
"metadata": {},
"outputs": [],
"source": [
"model = Transformer.from_folder(model_path, dtype=torch.bfloat16)\n",
"mistral_tokenizer = MistralTokenizer.from_file(str(model_path / \"tokenizer.model\ "))\n",
"tokenizer = mistral_tokenizer.instruct_tokenizer.tokenizer"
]
},
{
"cell_type": "markdown",
"id": "4a9aa34b-cbe3-49a6-948b-17f6c84d93c6",
"metadata": {},
"source": [
"The tokenizer is a critical component of the model that segments input text into word-pieces.\n",
"\n",
"For instance, the sentence `\"Roasted barramundi fish\ "` is encoded as `['▁Ro', 'asted', '▁barr', 'am', 'und', 'i', '▁fish']`.\n",
"\n",
"The number of subwords in the model is set to `32000`, and each word is decomposed into known word pieces to avoid unknown words."
]
},
{
"cell_type": "markdown",
"id": "ce0e03ef-439f-4078-a848-d69bf4e339ec",
"metadata": {},
"source": [
"## Load the dataset"
]
},
{
"cell_type": "markdown",
"id": "65d1f696-138d-467d-bb53-032e08d47bf1",
"metadata": {},
"source": [
"We reload the Kaggle dataset from the disk. Each sample is composed of a sentence and a label. The dataset contains 24 different labels."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "cc2bf18b-d99c-4c31-9988-1675d019e04b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Reloaded 1200 samples with 24 labels.\n"
]
}
],
"source": [
"data = [] # list of (text, label)\n",
"with open(data_path, newline='') as csvfile:\n",
" reader = csv.reader(csvfile)\n",
" for i, row in enumerate(reader):\n",
" if i == 0: # skip csv header\n",
" continue\n",
" data.append((row[2], row[1]))\n",
"\n",
"# label text to label ID\n",
"labels = sorted({x[1] for x in data})\n",
"txt_to_label = {x: i for i, x in enumerate(labels)}\n",
"print(f\"Reloaded { len(data)} samples with { len(labels)} labels.\ ")\n",
"\n",
"# integer class for each datapoint\n",
"data_class = [txt_to_label[x[1]] for x in data]"
]
},
{
"cell_type": "markdown",
"id": "c5434265-fad8-4daa-b54b-438d420bcb4d",
"metadata": {},
"source": [
"The task is to classify a symptom, for instance `\"I have a dry cough that never stops.\ "` to one of the 24 disease labels (`Acne, Arthritis, Bronchial Asthma, Cervical spondylosis, Chicken pox, Common Cold, etc.`)."
]
},
{
"cell_type": "markdown",
"id": "1540b537-c3cc-4851-80e3-91a9b9e8cc7c",
"metadata": {},
"source": [
"## Embed data points in the dataset"
]
},
{
"cell_type": "markdown",
"id": "c73d5d75-55eb-4210-8ffe-d0db3e9f8735",
"metadata": {},
"source": [
"We will now learn a linear classifier on frozen features provided by Mistral 7B.\n",
"In particular, each sentence in the dataset will be tokenized, and provided to the model.\n",
"\n",
"If the input sentence is composed of `N` tokens, the model output will be a list of `N` vectors of dimension `d=4096`, where `d` is the dimensionality of the model.\n",
"These vectors are then averaged along the dimension 0 to get a vector of size `d`.\n",
"\n",
"Finally, the vectors of all sentences in the dataset are concatenated into a matrix of shape `(D, d)` where `D` is the number of samples in the dataset (in particular, D=1200)."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "78019021-01d7-499f-94ea-a3c88bbcb42c",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"1200it [00:25, 46.65it/s]\n"
]
}
],
"source": [
"with torch.no_grad():\n",
" featurized_x = []\n",
" # compute an embedding for each sentence\n",
" for i, (x, y) in tqdm.tqdm(enumerate(data)):\n",
" tokens = tokenizer.encode(x, bos=True)\n",
" tensor = torch.tensor(tokens).to(model.device)\n",
" features = model.forward_partial(tensor, [len(tokens)]) # (n_tokens, model_dim)\n",
" featurized_x.append(features.float().mean(0).cpu().detach().numpy())\n",
"\n",
"# concatenate sentence embeddings\n",
"X = np.concatenate([x[None] for x in featurized_x], axis=0) # (n_points, model_dim)"
]
},
{
"cell_type": "markdown",
"id": "7a997101-7844-4928-bdf4-d7a3051eca75",
"metadata": {},
"source": [
"## Plot t-SNE embeddings"
]
},
{
"cell_type": "markdown",
"id": "61bbc6b4-dfc5-42e0-b99b-1ed281d929cb",
"metadata": {},
"source": [
"Now that we have one vector/embedding for each sample in our dataset, we can visualize them using t-SNE.\n",
"t-SNE is a powerful tool for reducing the dimensionality of high-dimensional data, while preserving the underlying structure and relationships between the data points, which can help uncover patterns and insights that would be difficult to discern in the high-dimensional space.\n",
"\n",
"In the graph below, we assign a different color to each class in the dataset. It is apparent that several distinct clusters are visible in the data."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8e3cd894-ac30-4f34-a4c8-ef34293b587d",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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 | | |
