Initial application upload

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,12 @@
+# Environment variables and secrets
+.env
+
+# Jupyter Notebook checkpoints
+.ipynb_checkpoints/
+
+# Local log/run directories
+runs/
+
+# Python cache
+__pycache__/
+*.pyc

Dockerfile

@@ -0,0 +1,18 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /code
+
+# Copy the requirements file into the container
+COPY ./requirements.txt /code/requirements.txt
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Copy the rest of your application's code and model files into the container
+COPY . /code/
+
+# Set the command to run your app using gunicorn, a production-ready server
+# We use port 7860 as it's standard for Hugging Face Spaces
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,46 @@
+import os
+from flask import Flask, request, jsonify
+from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
+from flask_cors import CORS
+
+app = Flask(__name__)
+CORS(app)
+
+# --- CHANGE IS HERE ---
+# Define the local directory path where your model files are located.
+# The "." means the current directory.
+local_model_path = "."
+print(f"Loading model from local path: {local_model_path}")
+
+# Load the model and tokenizer from the local directory
+try:
+    tokenizer = AutoTokenizer.from_pretrained(local_model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(local_model_path)
+    classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+    print("Model loaded successfully.")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    # If the model fails to load, we can't run the app. Exit or handle appropriately.
+    classifier = None
+
+@app.route('/analyze', methods=['POST'])
+def analyze_sentiment():
+    if not classifier:
+         return jsonify({"error": "Model could not be loaded. Check server logs."}), 500
+
+    data = request.json
+    text = data.get('text', '')
+
+    if not text:
+        return jsonify({"error": "No text provided"}), 400
+
+    try:
+        result = classifier(text)
+        return jsonify(result)
+    except Exception as e:
+        print(f"Error during analysis: {e}")
+        return jsonify({"error": str(e)}), 500
+
+if __name__ == '__main__':
+    port = int(os.environ.get("PORT", 8080))
+    app.run(host='0.0.0.0', port=port)

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b61385e4482edd179b69042c014dcb53a79431784f34a0171f5d43b092feaa
+size 328499560

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d24cd7c45f0b65241fd9ff1aa97814eea3ab7bdbf1458248fb9f4b2c817864
+size 328529005

requirements.txt

@@ -0,0 +1,10 @@
+flask==2.0.1
+flask-cors==3.0.10
+transformers>=4.35.0
+torch>=2.0.0
+torchvision>=0.15.0
+datasets>=1.12.1
+tokenizers>=0.13.0
+werkzeug>=2.0.0,<2.1.0 
+sentencepiece
+gunicorn

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1178219233a39de3467c1d1c9ad2fd1d976e51b9ed6bb5a459131607445eaf
+size 2735