Upload README.md with huggingface_hub

README.md

@@ -11,15 +11,37 @@ tags:
   - qwen
   - fine-tuned
 base_model: Qwen/Qwen2.5-0.5B
+widget:
+  - text: "### System:\nYou are a bank transaction classifier for Indian bank statements. Given a raw transaction description, infer both its category and the actual company when evidence exists. Respond with ONLY a JSON object: {\"category\": \"<category>\", \"company_name\": \"<company_or_null>\", \"is_income\": false, \"confidence\": 0.0}.\n\n### Input:\nUPI/zerodhabroking@/HDFC BANK LTD\n\n### Output:\n"
+    example_title: "UPI — Zerodha"
+  - text: "### System:\nYou are a bank transaction classifier for Indian bank statements. Given a raw transaction description, infer both its category and the actual company when evidence exists. Respond with ONLY a JSON object: {\"category\": \"<category>\", \"company_name\": \"<company_or_null>\", \"is_income\": false, \"confidence\": 0.0}.\n\n### Input:\nNEFT/SALARY/ACME CORP\n\n### Output:\n"
+    example_title: "NEFT — Salary"
 ---
 
 # Indian Transaction Classifier
 
 Fine-tuned Qwen2.5-0.5B for classifying Indian bank transactions (UPI, NEFT, IMPS, RTGS) into 30+ categories with merchant identification.
 
-## Model Description
+## ⚡ Try it now (Inference API — free, no setup)
 
-This model is fine-tuned on 1,700 privacy-sanitized Indian bank transaction descriptions. It classifies transactions into categories like salary, food, grocery, trading, bills, etc. and identifies the merchant/company when possible.
+Use the **Inference API** widget on the right side of this page. Type a transaction description in the text box and click Compute.
+
+Or call it programmatically:
+
+```python
+from huggingface_hub import InferenceClient
+
+client = InferenceClient(model="SahilGoel/indian-txn-classifier")
+
+system_prompt = 'You are a bank transaction classifier for Indian bank statements. Given a raw transaction description, infer both its category and the actual company when evidence exists. Respond with ONLY a JSON object: {"category": "<category>", "company_name": "<company_or_null>", "is_income": false, "confidence": 0.0}.'
+
+tx = "UPI/zerodhabroking@/HDFC BANK LTD"
+prompt = f"### System:\n{system_prompt}\n\n### Input:\n{tx}\n\n### Output:\n"
+
+result = client.text_generation(prompt, max_new_tokens=100, temperature=0.1)
+print(result)
+# {"category": "trading_deposit", "company_name": "Zerodha", "is_income": false, "confidence": 0.95}
+```
 
 ## Categories
 
@@ -29,7 +51,17 @@ This model is fine-tuned on 1,700 privacy-sanitized Indian bank transaction desc
 
 **Special:** friends, family, flat_deposit, trading_fees, vehicle_purchase, staff_salary, health_fitness, transfer, unclassified
 
-## Usage
+## Pipeline Architecture
+
+1. **Rule engine** (70-80% coverage) — regex patterns for known merchants and UPI handles
+2. **Recurring pattern detector** (10% more) — identifies repeating transactions
+3. **Fine-tuned Qwen 0.5B** (remaining) — LLM fallback for uncertain transactions
+
+## Run locally
+
+```bash
+pip install transformers torch
+```
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -38,24 +70,17 @@ model = AutoModelForCausalLM.from_pretrained("SahilGoel/indian-txn-classifier")
 tokenizer = AutoTokenizer.from_pretrained("SahilGoel/indian-txn-classifier")
 
 system_prompt = "You are a bank transaction classifier for Indian bank statements..."
-
-input_text = "UPI/zerodhabroking@/HDFC BANK LTD"
+input_text = "UPI/swiggybengaluru@/HDFC BANK LTD"
 prompt = f"### System:\n{system_prompt}\n\n### Input:\n{input_text}\n\n### Output:\n"
 
 inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=100)
+outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.1, do_sample=False)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-## Training Data
-
-1,700 privacy-sanitized transaction descriptions. PII (phone numbers, personal UPI handles, reference numbers) has been redacted.
-
-## Pipeline Architecture
+## Run on Google Colab (free GPU)
 
-1. **Rule engine** (70-80% coverage) - regex patterns for known merchants and UPI handles
-2. **Recurring pattern detector** (10% more) - identifies repeating transactions
-3. **Fine-tuned Qwen 0.5B** (remaining) - LLM fallback for uncertain transactions
+Open `app.py` from the GitHub repo in a Colab notebook — it works as a Gradio app with a public share link.
 
 ## Supported Banks