Add model files and exclude large training files with .gitignore

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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

.gitignore

@@ -0,0 +1,6 @@
+# Exclude large training files that aren't needed for inference
+model_chekpoint/optimizer.pt
+model_chekpoint/rng_state.pth
+model_chekpoint/scheduler.pt
+model_chekpoint/trainer_state.json
+model_chekpoint/training_args.bin

README.md

@@ -10,4 +10,4 @@ pinned: false
 short_description: ProsusAI/finbert finetuned just for test
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-references

app.py

@@ -1,7 +1,58 @@
 import gradio as gr
+import torch
+from utils import load_model_from_checkpoint, get_device
 
-def greet(name):
-    return "Hello " + name + "!!"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+def predict_sentiment(text):
+    """
+    Predict sentiment of the input text using the loaded model.
+    
+    Args:
+        text (str): Input text to analyze
+        
+    Returns:
+        str: Sentiment prediction
+    """
+    try:
+        # Load model and tokenizer
+        model, tokenizer = load_model_from_checkpoint()
+        device = get_device()
+        model = model.to(device)
+        
+        # Tokenize input text
+        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+        inputs = {k: v.to(device) for k, v in inputs.items()}
+        
+        # Get prediction
+        with torch.no_grad():
+            outputs = model(**inputs)
+            predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+            predicted_class = torch.argmax(predictions, dim=-1).item()
+            
+        # Map class to sentiment (adjust based on your model's classes)
+        sentiment_map = {0: "Negative", 1: "Positive", 2: "Neutral"}
+        sentiment = sentiment_map.get(predicted_class, "Unknown")
+        confidence = predictions[0][predicted_class].item()
+        
+        return f"Sentiment: {sentiment} (Confidence: {confidence:.2f})"
+        
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=predict_sentiment,
+    inputs="text",
+    outputs="text",
+    title="Financial Sentiment Analysis",
+    description="Enter financial text to analyze sentiment using the finetuned FinBERT model.",
+    examples=[
+        "The stock market is performing well today.",
+        "The company's earnings report was disappointing.",
+        "Investors are optimistic about the future prospects."
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch()

config.yaml

@@ -0,0 +1 @@
+model_path: "model_checkpoint"

model_chekpoint/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "ProsusAI/finbert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "positive",
+    "1": "negative",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 1,
+    "neutral": 2,
+    "positive": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model_chekpoint/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

model_chekpoint/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

utils.py

@@ -0,0 +1,55 @@
+import os
+import yaml
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+
+def load_model_from_checkpoint():
+    """
+    Load model from transformers checkpoint.
+    The checkpoint location is specified by model_path in config.yaml.
+    
+    Returns:
+        tuple: (model, tokenizer) loaded from the checkpoint
+    """
+    # Read config to get model_path
+    config_path = "config.yaml"
+    if not os.path.exists(config_path):
+        raise FileNotFoundError(f"Config file not found: {config_path}")
+    
+    with open(config_path, 'r') as f:
+        config = yaml.safe_load(f)
+    
+    model_path = config.get('model_path')
+    if not model_path:
+        raise ValueError("model_path not found in config.yaml")
+    
+    # Check if checkpoint directory exists
+    if not os.path.exists(model_path):
+        raise FileNotFoundError(f"Model checkpoint not found at: {model_path}")
+    
+    # Load tokenizer and model from the checkpoint
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_path)
+        model = AutoModelForSequenceClassification.from_pretrained(model_path)
+        
+        # Set model to evaluation mode
+        model.eval()
+        
+        return model, tokenizer
+        
+    except Exception as e:
+        raise RuntimeError(f"Failed to load model from checkpoint {model_path}: {str(e)}")
+
+
+def get_device():
+    """
+    Get the appropriate device for model inference.
+    
+    Returns:
+        torch.device: Device to use for inference
+    """
+    if torch.cuda.is_available():
+        return torch.device('cuda')
+    else:
+        return torch.device('cpu')