Upload folder using huggingface_hub

app.py

@@ -1,31 +1,37 @@
 # Apache Software License 2.0
-# 
+#
 # Copyright (c) ZenML GmbH 2023. All rights reserved.
-# 
+#
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
-# 
+#
 # http://www.apache.org/licenses/LICENSE-2.0
-# 
+#
 # Unless required by applicable law or agreed to in writing, software
 # distributed under the License is distributed on an "AS IS" BASIS,
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-# 
+from os.path import dirname
+from typing import Optional
 
 import click
 import numpy as np
-import os
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
-from os.path import dirname
 
 import gradio as gr
 
+
 @click.command()
-@click.option("--tokenizer_name_or_path", default="tokenizer", help="Name or the path of the tokenizer.")
-@click.option("--model_name_or_path", default="model", help="Name or the path of the model.")
+@click.option(
+    "--tokenizer_name_or_path",
+    default="tokenizer",
+    help="Name or the path of the tokenizer.",
+)
+@click.option(
+    "--model_name_or_path", default="model", help="Name or the path of the model."
+)
 @click.option(
     "--labels", default="Negative,Positive", help="Comma-separated list of labels."
 )
@@ -34,7 +40,7 @@ import gradio as gr
 )
 @click.option(
     "--description",
-    default="Sentiment Analyzer",
+    default="Text Classification - Sentiment Analysis - ZenML - Gradio",
     help="Description of the Gradio interface.",
 )
 @click.option(
@@ -45,15 +51,44 @@ import gradio as gr
 @click.option(
     "--examples",
     default="This is an awesome journey, I love it!",
-    help="Comma-separated list of examples to show in the Gradio interface.",
+    help="An example to show in the Gradio interface.",
 )
 def sentiment_analysis(
-    tokenizer_name_or_path, model_name_or_path, labels, title, description, interpretation, examples
+    tokenizer_name_or_path: Optional[str],
+    model_name_or_path: Optional[str],
+    labels: Optional[str],
+    title: Optional[str],
+    description: Optional[str],
+    interpretation: Optional[str],
+    examples: Optional[str],
 ):
+    """Launches a Gradio interface for sentiment analysis.
+
+    This function launches a Gradio interface for text-classification.
+    It loads a model and a tokenizer from the provided paths and uses
+    them to predict the sentiment of the input text.
+
+    Args:
+        tokenizer_name_or_path (str): Name or the path of the tokenizer.
+        model_name_or_path (str): Name or the path of the model.
+        labels (str): Comma-separated list of labels.
+        title (str): Title of the Gradio interface.
+        description (str): Description of the Gradio interface.
+        interpretation (str): Interpretation mode for the Gradio interface.
+        examples (str): Comma-separated list of examples to show in the Gradio interface.
+    """
     labels = labels.split(",")
     examples = [examples]
 
-    def preprocess(text):
+    def preprocess(text: str) -> str:
+        """Preprocesses the text.
+
+        Args:
+            text (str): Input text.
+
+        Returns:
+            str: Preprocessed text.
+        """
         new_text = []
         for t in text.split(" "):
             t = "@user" if t.startswith("@") and len(t) > 1 else t

model/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/Users/safoine-zenml/Library/Application Support/zenml/local_stores/7f2168ca-a26f-456a-ad57-df9f92cd8d69/mlruns/321726471800252444/bb06b501b2ec4d0d9d4b03d2403b2886/artifacts/nlp_use_case_model/model",
+  "_name_or_path": "/var/folders/lt/r3j8hp4s00dfgtf662d1prw80000gp/T/tmp7zaefx9s",
   "architectures": [
     "RobertaForSequenceClassification"
   ],

model/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254eea426065025dfb31cb3823d55a8881fed3fa838ed9f02214c19215a8ef26
+oid sha256:725bbeee72c1021836a2417dd029c13df44d2b0c6becd17c207e597ae6c078d6
 size 498655278

serve.yaml

@@ -1,6 +1,15 @@
 # Task name (optional), used for display purposes.
-name: nlp_use_case
+name: ZenML NLP project}
 
+resources:
+  cloud: aws  # The cloud to use (optional).
+
+  # The region to use (optional). Auto-failover will be disabled
+  # if this is specified.
+  region: us-east-1
+
+  # The instance type to use (optional).
+  instance_type: t3.large
 # Working directory (optional), synced to ~/sky_workdir on the remote cluster
 # each time launch or exec is run with the yaml file.
 #
@@ -16,13 +25,5 @@ setup: |
   echo "Setup complete."
 
 run: |
-  conda activate vllm
-  echo 'Starting vllm api server...'
-  python -u -m app.py \
-                   ----tokenizer_name $MODEL_NAME \
-                   --tensor-parallel-size $SKYPILOT_NUM_GPUS_PER_NODE \
-                   --tokenizer hf-internal-testing/llama-tokenizer 2>&1 | tee api_server.log &
-  echo 'Waiting for vllm api server to start...'
-  while ! `cat api_server.log | grep -q 'Uvicorn running on'`; do sleep 1; done
-  echo 'Starting gradio server...'
-  python vllm/examples/gradio_webserver.py
+  echo 'Starting gradio app...'
+  python app.py