Views
No views yet
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained(
4 "Ranjit0034/finee-llama-8b",
5 torch_dtype="auto",
6 device_map="auto"
7)
8tokenizer = AutoTokenizer.from_pretrained("Ranjit0034/finee-llama-8b")
9
10message = "HDFC Bank: Rs.2,500 debited from A/c XX1234 on 12-Jan-26. UPI:swiggy@ybl. Ref:123456789012"
11
12prompt = f"""Extract financial entities from this message:
13
14{message}
15
16JSON:"""
17
18inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
19outputs = model.generate(**inputs, max_new_tokens=256)
20result = tokenizer.decode(outputs[0], skip_special_tokens=True)
21print(result)1from mlx_lm import load, generate
2
3model, tokenizer = load("Ranjit0034/finee-llama-8b")
4output = generate(model, tokenizer, prompt, max_tokens=256)
5print(output)1from finee import FinancialExtractor
2
3extractor = FinancialExtractor(model="Ranjit0034/finee-llama-8b")
4result = extractor.extract("HDFC Bank: Rs.2,500 debited...")
5print(result)
6# {'amount': 2500.0, 'type': 'debit', 'merchant': 'Swiggy', 'category': 'food'}1{
2 "amount": 2500.0,
3 "type": "debit",
4 "account": "1234",
5 "bank": "HDFC",
6 "date": "2026-01-12",
7 "reference": "123456789012",
8 "merchant": "Swiggy",
9 "vpa": "swiggy@ybl",
10 "category": "food",
11 "is_p2m": true
12}| Metric | Score |
|---|---|
| Amount Accuracy | 99.2% |
| Type Accuracy | 98.5% |
| Merchant Detection | 92.3% |
| Category Accuracy | 88.7% |
| Overall F1 | 94.8% |