Instructions to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF",
	filename="gemma-4-E2B-it.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

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 TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

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 TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

Use Docker

docker model run hf.co/TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

LM Studio
Jan

vLLM

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

Ollama
How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with Ollama:
```
ollama run hf.co/TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16
```

Unsloth Studio new

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF 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 TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF 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 TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF to start chatting

Pi new

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

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": "TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

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 TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

Run Hermes

hermes

Docker Model Runner
How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with Docker Model Runner:
```
docker model run hf.co/TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16
```

Lemonade

How to use TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF:BF16

Run and chat with the model

lemonade run user.gemma-4-E2B-sec-extraction-GGUF-BF16

List all available models

lemonade list

DEPRECATED — Please use gemma-4-E2B-sec-extraction-GGUF-v2 instead.

v2 was trained on a combined instruction + corrective dataset (3,957 examples vs. 2,726) and shows measurably stronger extraction quality, including a 2 percentage point reduction in hallucination rate versus the base Gemma 4 E2B model (10.7% vs. 12.7%). v2 also improves symbol compliance (+0.9%), reduces bare number errors (-0.8%), and eliminates year-as-value hallucinations entirely.

This v1 model remains available for reproducibility but is no longer recommended for production use.

Gemma 4 E2B — SEC Financial Extraction (v1, GGUF) [DEPRECATED]

A fine-tuned Gemma 4 E2B model specialized for extracting structured financial data from SEC Exhibit 10 material contracts. Quantized to Q4_K_M GGUF for efficient local inference.

What This Model Does

Given raw text from an SEC filing (employment agreements, credit facilities, merger agreements, etc.), this model extracts structured JSON containing:

Metadata — effective dates and contracting party names
Financial terms — dollar amounts and percentages classified into 13 categories (salary, bonus, severance, equity_grant, credit_facility, interest_rate, etc.)
Debt covenants — financial maintenance tests classified into 7 categories (leverage_ratio, interest_coverage, debt_service, net_worth, etc.)

Why You Should Use v2 Instead

Metric	v1	v2	Delta
Hallucination phrase rate	—	10.7% (vs 12.7% base)	-2.0pp
Symbol compliance	—	84.3% (vs 83.4% base)	+0.9pp
Bare number rate	—	8.8% (vs 9.6% base)	-0.8pp
Year-as-value errors	—	0 (vs 1 base)	Eliminated
Training examples	2,726	3,957	+45%
Training signal	Positive only	Positive + corrective + hard negatives	Richer

v2 is a strict upgrade — same base model, same hardware requirements, better extraction quality across all measured dimensions.

Upgrade: TheTokenFactory/gemma-4-E2B-sec-extraction-GGUF-v2

Usage

LM Studio

Download gemma-4-E2B-it.Q4_K_M.gguf (3.4 GB)
Import into LM Studio
Set GPU Layers to max (35/35), Context Length to 4096
Send extraction prompts via the chat API at http://localhost:1234/v1

Python (via OpenAI-compatible API)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:1234/v1", api_key="lm-studio")

response = client.chat.completions.create(
    model="gemma",
    temperature=0.1,
    messages=[
        {"role": "system", "content": "You are a financial analyst AI. Extract ALL monetary dollar amounts and financial percentages. Output strictly as JSON."},
        {"role": "user", "content": "<contract text here>"},
    ],
)
print(response.choices[0].message.content)

Training Details

Parameter	Value
Base model	`unsloth/gemma-4-E2B-it`
Method	QLoRA (4-bit) via Unsloth
LoRA rank	8
LoRA alpha	8
Epochs	3
Learning rate	2e-4
Max sequence length	2,048 tokens
Training examples	2,726 (positive only)
Quantization	Q4_K_M
Hardware	Google Colab T4 (16 GB VRAM)

Financial Term Types (13 categories)

salary bonus severance retirement_benefit equity_grant credit_facility loan_amount interest_rate fee threshold purchase_price compensation other

Covenant Types (7 categories)

leverage_ratio interest_coverage debt_service net_worth liquidity fixed_charge other

Hardware Requirements

Setup	VRAM	Notes
RTX 4050 / 4060 (6 GB)	3.4 GB model + KV cache	Full GPU offload, 4096 context
RTX 3060 / 4070 (8+ GB)	Comfortable headroom
CPU-only	~4 GB RAM	Slower, but works

Limitations

Temporal scope: Trained on S&P 500 filings from a 6-month window
Universe: Large-cap US equities only (S&P 500)
Language: English only
Label quality: Silver-standard (model-generated, not human-annotated)
No corrective training: v1 was trained only on positive examples, without the corrective/hard-negative signal that improves v2

License

CC-BY-4.0. SEC filings are public domain; this model's value is in the fine-tuning for structured extraction.

Trained 2x faster with Unsloth

Downloads last month: 194

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

TheTokenFactory
/

gemma-4-E2B-sec-extraction-GGUF