gokulalex commited on
Commit
7fca437
Β·
verified Β·
1 Parent(s): b4f79fd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -7
README.md CHANGED
@@ -1,10 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
- title: README
3
- emoji: πŸ‘€
4
- colorFrom: red
5
- colorTo: indigo
6
- sdk: docker
7
- pinned: false
 
 
 
 
8
  ---
9
 
10
- Edit this `README.md` markdown file to author your organization card.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!--
2
+ SimplyFI β€’ Organization Card (Hugging Face)
3
+ Usage: put this README.md inside a Space named `README` under your org.
4
+ Assets to add in the same Space repo:
5
+ /assets/simplyfi-banner.png
6
+ /assets/simplyfi-logo.png
7
+ Replace bracketed placeholders like [link] / [email].
8
+ -->
9
+
10
+ <p align="center">
11
+ <img src="./assets/simplyfi-banner.png" alt="SimplyFI β€” AI Agents for Banking" width="100%" />
12
+ </p>
13
+
14
+ <h1 align="center">SimplyFI β€” AI Agents for Banking</h1>
15
+
16
+ <p align="center">
17
+ Intelligent automation for <b>Customer Engagement</b>, <b>Compliance</b>, <b>Lending</b>, and <b>Trade Finance</b>.<br/>
18
+ Models, datasets, and Spaces for document understanding, risk, and decisioning β€” production-first and audit-ready.
19
+ </p>
20
+
21
+ <p align="center">
22
+ <a href="[website]"><img alt="Website" src="https://img.shields.io/badge/Website-SimplyFI-blue.svg"></a>
23
+ <a href="[linkedin]"><img alt="LinkedIn" src="https://img.shields.io/badge/LinkedIn-@SimplyFI-informational.svg"></a>
24
+ <a href="mailto:[email]"><img alt="Contact" src="https://img.shields.io/badge/Contact-hello%40simplyfi.in-success.svg"></a>
25
+ <img alt="Industry" src="https://img.shields.io/badge/Industry-Banking%20%26%20Financial%20Services-8A2BE2.svg">
26
+ </p>
27
+
28
  ---
29
+
30
+ ## What we publish
31
+
32
+ - **Models**: OCR/IE, invoice understanding, entity linking (KYC/AML), credit signals, dialogue agents (RAG+RLHF).
33
+ - **Datasets**: Synthetic & anonymized corpora for invoices, SWIFT/LC patterns, trade compliance, FAQs.
34
+ - **Spaces**: Demo apps for **document triage**, **explainable decisions**, and **agentic workflows**.
35
+ - **Notebooks**: End-to-end examples β€” from fine-tuning to human feedback (RLHF) and safe deployment.
36
+
37
+ > Prefer **bank-grade** controls? We support **gated access**, **EULAs**, and **private org Spaces** for sensitive assets.
38
+
39
  ---
40
 
41
+ ## Highlights
42
+
43
+ - **SIMBA** β€” our production platform for **Trade Finance & Banking AI**: OCR ➜ extraction ➜ validation ➜ decisioning
44
+ - **Agentic Workflows** β€” multi-tool agents with grounded retrieval, guardrails, and human-in-the-loop review
45
+ - **Compliance by design** β€” redaction, PII handling, lineage, prompt/trace logging, and model cards with usage guidance
46
+
47
+ ---
48
+
49
+ ## Explore
50
+
51
+ ### Featured models
52
+ | Purpose | Model | Tasks | Notes |
53
+ |---|---|---|---|
54
+ | Invoice Understanding | [`SimplyFI/invoice-extractor`](https://huggingface.co/SimplyFI/invoice-extractor) | token-classification, table-qa | line-item, taxes, totals, vendor |
55
+ | Trade Compliance NER | [`SimplyFI/trade-ner-compliance`](https://huggingface.co/SimplyFI/trade-ner-compliance) | token-classification | sanctions terms, ports, HS codes |
56
+ | Banking Assistant (SFT) | [`SimplyFI/banking-assistant-sft`](https://huggingface.co/SimplyFI/banking-assistant-sft) | text-generation | safe, concise answers with citations |
57
+ | Risk Signals | [`SimplyFI/risk-signal-classifier`](https://huggingface.co/SimplyFI/risk-signal-classifier) | sequence-classification | escalations & review routing |
58
+
59
+ > Replace links above with your actual repos (or keep as placeholders until published).
60
+
61
+ ### Example: quick inference
62
+
63
+ ```python
64
+ from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline
65
+
66
+ repo = "SimplyFI/invoice-extractor" # update if different
67
+ tok = AutoTokenizer.from_pretrained(repo)
68
+ mdl = AutoModelForTokenClassification.from_pretrained(repo)
69
+ ner = pipeline("token-classification", model=mdl, tokenizer=tok, aggregation_strategy="simple")
70
+
71
+ text = "Invoice 9081 from Alpha Plastics Pvt Ltd, Total β‚Ή1,24,560 due on 2025-11-15"
72
+ print(ner(text))