Add CoreML sentiment analysis model

README.md

@@ -0,0 +1,76 @@
+---
+library_name: coreml
+tags:
+- coreml
+- sentiment-analysis
+- distilbert
+- text-classification
+license: apache-2.0
+---
+
+# sentiment-analyzer-coreml
+
+This is a CoreML version of the DistilBERT sentiment analysis model, converted from the Hugging Face model `distilbert-base-uncased-finetuned-sst-2-english`.
+
+## Model Details
+
+- **Original Model**: `distilbert-base-uncased-finetuned-sst-2-english`
+- **Task**: Sentiment Analysis
+- **Framework**: CoreML
+- **Input**: Text (tokenized as input_ids and attention_mask)
+- **Output**: Logits for sentiment classification (2 classes: negative, positive)
+
+## Usage
+
+### Python (CoreML)
+
+```python
+import coremltools as ct
+
+# Load the model
+model = ct.models.MLModel("sentiment_analyzer.mlpackage")
+
+# Get model spec
+spec = model.get_spec()
+print("Model type:", spec.WhichOneof('Type'))
+
+# Make predictions (you'll need to tokenize your input first)
+# The model expects input_ids and attention_mask as inputs
+```
+
+### Swift (iOS/macOS)
+
+```swift
+import CoreML
+
+// Load the model
+guard let model = try? MLModel(contentsOf: URL(fileURLWithPath: "sentiment_analyzer.mlpackage")) else { return }
+
+// Make predictions
+// You'll need to convert your text to the required input format
+```
+
+## Input Format
+
+The model expects two inputs:
+- `input_ids`: Tokenized input text (shape: [1, sequence_length])
+- `attention_mask`: Attention mask (shape: [1, sequence_length])
+
+## Output Format
+
+The model outputs logits for sentiment classification:
+- Shape: [1, 2] (batch_size, num_classes)
+- Classes: [negative, positive]
+
+## Conversion Notes
+
+This model was converted using coremltools from the original PyTorch model. The conversion process involved:
+1. Loading the Hugging Face model
+2. Wrapping it to return only logits (tensor output)
+3. Tracing with PyTorch JIT
+4. Converting to CoreML format
+
+## Requirements
+
+- iOS 15+ / macOS 12+ (for ML Program format)
+- CoreML framework

config.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "coreml",
+  "task": "text-classification",
+  "library_name": "coreml",
+  "tags": [
+    "coreml",
+    "sentiment-analysis",
+    "distilbert",
+    "text-classification"
+  ],
+  "pipeline_tag": "text-classification",
+  "original_model": "distilbert-base-uncased-finetuned-sst-2-english",
+  "framework": "coreml"
+}

sentiment_analyzer.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1aa11aff34987ce108498e4b097433862108ceaeeb5ecfba8c0894c72c18fa8
+size 72807

sentiment_analyzer.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdda8f2fe4d312a43a583c007a51cb9955e14c28ca7aacb878e2e1e63a58380b
+size 133140992

sentiment_analyzer.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "02da44c3-3204-4c7f-940c-d0e3b357c7ab": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "67433d37-6b4d-4083-96a8-daca42182fc0": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "67433d37-6b4d-4083-96a8-daca42182fc0"
+}