Instructions to use newdim001/sba-extract-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use newdim001/sba-extract-v4 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf newdim001/sba-extract-v4
# Run inference directly in the terminal:
llama cli -hf newdim001/sba-extract-v4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf newdim001/sba-extract-v4
# Run inference directly in the terminal:
llama cli -hf newdim001/sba-extract-v4

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf newdim001/sba-extract-v4
# Run inference directly in the terminal:
./llama-cli -hf newdim001/sba-extract-v4

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf newdim001/sba-extract-v4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf newdim001/sba-extract-v4

Use Docker

docker model run hf.co/newdim001/sba-extract-v4

LM Studio
Jan

vLLM

How to use newdim001/sba-extract-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "newdim001/sba-extract-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "newdim001/sba-extract-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/newdim001/sba-extract-v4

Ollama
How to use newdim001/sba-extract-v4 with Ollama:
```
ollama run hf.co/newdim001/sba-extract-v4
```

Unsloth Studio

How to use newdim001/sba-extract-v4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for newdim001/sba-extract-v4 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for newdim001/sba-extract-v4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for newdim001/sba-extract-v4 to start chatting

How to use newdim001/sba-extract-v4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf newdim001/sba-extract-v4

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "newdim001/sba-extract-v4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use newdim001/sba-extract-v4 with Docker Model Runner:
```
docker model run hf.co/newdim001/sba-extract-v4
```

Lemonade

How to use newdim001/sba-extract-v4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull newdim001/sba-extract-v4

Run and chat with the model

lemonade run user.sba-extract-v4-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use newdim001/sba-extract-v4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf newdim001/sba-extract-v4

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default newdim001/sba-extract-v4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use newdim001/sba-extract-v4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf newdim001/sba-extract-v4

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "newdim001/sba-extract-v4" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

sba-extract-v4 — SBA Form 413 Field Extractor

A fine-tuned Qwen2.5-3B model that extracts 16 financial fields from US tax returns into structured JSON for SBA Form 413 (Personal Financial Statement). Built for community banks and credit unions automating small business lending.

What it does

Feed it a tax return (text or markdown) → get structured JSON:

{
  "name": "John M Smith",
  "ssn": "123-45-6789",
  "employer": "ACME Technologies Inc",
  "annual_income": 125000,
  "cash": 120000,
  "real_estate": 650000,
  "mortgages": 450000,
  "stocks_bonds": 120000,
  "retirement_accounts": 250000,
  "life_insurance": 35000,
  "notes_receivable": 10000,
  "credit_card_debt": 8500,
  "auto_loans": 25000,
  "total_assets": 1185000,
  "total_liabilities": 483500,
  "net_worth": 701500
}

Accuracy

Metric	Score
Raw field accuracy	81% (13/16 exact)
With post-processing	100% (16/16, includes multi-value sum + regex totals)
Name/SSN/Employer	100%
Income/Asset extraction	78-85% confidence per field

The 3 partial misses are multi-value fields (e.g., two bank accounts, two properties) — the model picks the first value. The Forms SBA platform fixes this with a post-processing sum-of-parts rule.

Model details

Parameter	Value
Base architecture	Qwen2
Parameter count	3.1B (3,085,938,688)
Context length	32,768 tokens
Quantization	F16 (full precision, zero loss)
Format	GGUF v2
Attention	GQA (16 query heads, 2 KV heads)
Layers	36
File size	6.2 GB

Quick start

Option 1: Ollama

ollama pull hf.co/newdim001/sba-extract-v4
ollama run sba-extract-v4

Option 2: llama.cpp

llama-cli \
  -m sba-extract-v4.gguf \
  -p "Extract SBA Form 413 fields from: FORM 1040 - John Smith SSN 123-45-6789 Wages: 125000 Cash: 45000..."

Option 3: Python (recommended prompt)

prompt = """
### Instruction:
Extract ALL SBA Form 413 fields from the tax return below. Return ONLY valid JSON with these 16 fields:
- name, ssn, employer, annual_income, cash, real_estate, mortgages
- stocks_bonds, retirement_accounts, life_insurance, notes_receivable
- credit_card_debt, auto_loans, total_assets, total_liabilities, net_worth

### Input:
{your_tax_return_text}

### Response:
"""

Built by

Koodo Technology LLC FZ (Dubai) — part of the Forms SBA platform. Automated SBA lending for US community banks and credit unions.

License

MIT

Downloads last month: 112

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for newdim001/sba-extract-v4

Base model

Qwen/Qwen2.5-3B

Quantized

(53)

this model

Evaluation results

Raw Field Accuracy on SBA Form 413 Tax Return Dataset
self-reported

81.000
Field Accuracy (with post-processing) on SBA Form 413 Tax Return Dataset
self-reported

100.000