Instructions to use Effectz-AI/Peoples-InvoiceLM-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Effectz-AI/Peoples-InvoiceLM-14B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Effectz-AI/Peoples-InvoiceLM-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Effectz-AI/Peoples-InvoiceLM-14B")
model = AutoModelForCausalLM.from_pretrained("Effectz-AI/Peoples-InvoiceLM-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Effectz-AI/Peoples-InvoiceLM-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Effectz-AI/Peoples-InvoiceLM-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Effectz-AI/Peoples-InvoiceLM-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Effectz-AI/Peoples-InvoiceLM-14B

SGLang

How to use Effectz-AI/Peoples-InvoiceLM-14B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Effectz-AI/Peoples-InvoiceLM-14B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Effectz-AI/Peoples-InvoiceLM-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Effectz-AI/Peoples-InvoiceLM-14B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Effectz-AI/Peoples-InvoiceLM-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Effectz-AI/Peoples-InvoiceLM-14B with Docker Model Runner:
```
docker model run hf.co/Effectz-AI/Peoples-InvoiceLM-14B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

People's InvoiceLM-14B

A specialised member of the People's LM family by Effectz.AI.

People's InvoiceLM-14B is a domain-specific fine-tuned model built on Qwen3-14B base model, optimised for template-free invoice understanding, structured data extraction, and real-world finance document workflows. It is designed for the messy reality of enterprise invoices: changing supplier formats, inconsistent field layouts, scanned documents, and operational data that must be reviewed before it reaches downstream systems.

People's InvoiceLM powers invoice intelligence capabilities within E-Flow, Effectz.AI's document execution platform.

About People's LM

People's LM is Effectz.AI's family of compact, specialised language models built for real-world business workflows in emerging markets — built for the document formats, suppliers, and operating environments that global AI tools often overlook. This model has been fine-tuned using Effectz.AI's proprietary synthetic invoice dataset.

Model Details


Base model	Qwen3-14B-Base
Fine-tuning and domain adaptation	Effectz.AI
Model family	People's LM
Primary use case	Invoice data extraction and validation
Availability	Proprietary / controlled access through Effectz.AI

Intended Use

People's InvoiceLM-14B is intended to extract structured fields from supplier invoices, including:

Invoice number, Date, Currency, Exchange rate, Subtotal
Purchase Order (PO) numbers
Goods Receive Note (GRN) numbers
Supplier and buyer/company names

Out-of-scope use

This model is not intended for general-purpose text generation, open-domain question answering, or use outside invoice/finance document workflows. Extracted output should be reviewed before being used in automated downstream systems.

How to Use

People's InvoiceLM-14B is served via a controlled Hugging Face Inference Endpoint as part of the Effectz.AI E-Flow platform. Access is not self-serve — contact Effectz.AI for access details.

from huggingface_hub import InferenceClient

client = InferenceClient(model="<inference-endpoint-url>", token="<HF_TOKEN>")

response = client.text_generation(
    prompt,
    max_new_tokens=600,
    temperature=0.0,
    do_sample=False,
)

Acknowledgements

Special thanks to the Qwen team for the strong Qwen3-14B base model, Unsloth for efficient fine tuning tooling.

License

People's InvoiceLM-14B is proprietary software and model weights owned by Effectz.AI Private Limited. Use, copying, redistribution, fine-tuning, derivative-model creation, commercial deployment, and reverse engineering are prohibited unless explicitly authorised in writing by Effectz.AI.

For licensing inquiries, contact Effectz.AI.

Downloads last month: 156

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for Effectz-AI/Peoples-InvoiceLM-14B

Base model

Qwen/Qwen3-14B-Base

Finetuned

(78)

this model