From de3e9a3497dcaf0ec97e7e531832b542e326bff1 Mon Sep 17 00:00:00 2001
From: "Abhi..." <8083613+AbhimanyuAryan@users.noreply.github.com>
Date: Wed, 10 Apr 2024 11:04:29 +0100
Subject: [PATCH] wip up-until map

---
 docs/src/pythonusers.md | 51 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 docs/src/pythonusers.md

diff --git a/docs/src/pythonusers.md b/docs/src/pythonusers.md
new file mode 100644
index 00000000..e78d51db
--- /dev/null
+++ b/docs/src/pythonusers.md
@@ -0,0 +1,51 @@
+# Tutorial for huggingface users from Python
+
+Text classification is a common NLP task that assigns a label or class to text. Some of the largest companies run text classification in production for a wide range of practical applications. One of the most popular forms of text classification is sentiment analysis, which assigns a label like 🙂 positive, 🙁 negative, or 😐 neutral to a sequence of text.
+
+This guide will show you how to:
+
+1. Finetune [DistilBERT](https://huggingface.co/distilbert-base-uncased) on the [IMDb](https://huggingface.co/datasets/imdb) dataset to determine whether a movie review is positive or negative.
+2. Use your finetuned model for inference.
+
+## Installation
+
+First, install the `Transformers.jl` package by running the following command:
+
+```julia
+using Pkg
+Pkg.add("Transformers")
+```
+
+Secondly, install the `HuggingFaceDatasets.jl` package by running the following command:
+
+```julia
+using Pkg
+Pkg.add("HuggingFaceDatasets")
+```
+
+The next step is to load a DistilBERT tokenizer to preprocess the `text` field:
+
+```julia
+using Transformers
+using Transformers.TextEncoders
+using Transformers.HuggingFace
+
+tokenizer = HuggingFace.load_tokenizer("distilbert-base-uncased")
+```
+
+## Load dataset
+
+
+### Start by loading the IMDb dataset from the 🤗 Datasets library:
+
+```julia
+train_data = load_dataset("imdb", split="train").with_format("julia")
+test_data = load_dataset("imdb", split="test").with_format("julia")
+
+train_data[1]
+```
+
+
+
+
+source: https://huggingface.co/docs/transformers/en/tasks/sequence_classification
\ No newline at end of file