Instructions to use DJLougen/granite4-tax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DJLougen/granite4-tax with Transformers:

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

pipe = pipeline("text-generation", model="DJLougen/granite4-tax")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DJLougen/granite4-tax")
model = AutoModelForCausalLM.from_pretrained("DJLougen/granite4-tax")
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

vLLM

How to use DJLougen/granite4-tax with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DJLougen/granite4-tax"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DJLougen/granite4-tax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DJLougen/granite4-tax

SGLang

How to use DJLougen/granite4-tax 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 "DJLougen/granite4-tax" \
    --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": "DJLougen/granite4-tax",
		"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 "DJLougen/granite4-tax" \
        --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": "DJLougen/granite4-tax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use DJLougen/granite4-tax 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 DJLougen/granite4-tax 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 DJLougen/granite4-tax to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DJLougen/granite4-tax to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DJLougen/granite4-tax",
    max_seq_length=2048,
)

Docker Model Runner
How to use DJLougen/granite4-tax with Docker Model Runner:
```
docker model run hf.co/DJLougen/granite4-tax
```

Granite 4 Tax

A fine-tuned version of IBM Granite 4.0 Tiny Preview specialized for U.S. tax law reasoning with IRC citation support.

Model Details

Base model: ibm-granite/granite-4.0-tiny-preview
Architecture: GraniteMoeHybridForCausalLM (Mamba + Attention hybrid, MoE with 62 experts, 6 active per token)
Hidden size: 1536
Layers: 40 (36 Mamba + 4 Attention)
Context length: 131,072 tokens
Precision: bfloat16

Training

Fine-tuned using Unsloth with LoRA (rank=16, alpha=16) on synthetic U.S. tax law Q&A data covering:

Individual taxation
Business entity taxation
Estate and gift tax
International tax (CFCs, GILTI, FDII)
Tax procedure and compliance

LoRA target modules: q_proj, k_proj, v_proj, o_proj, in_proj, out_proj

The model was trained using SFT (Supervised Fine-Tuning) with structured reasoning in IRAC format (Issue, Rule, Application, Conclusion) and IRC citation grounding.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "DJLougen/granite4-tax"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are a tax law assistant. Provide accurate analysis with IRC citations."},
    {"role": "user", "content": "What are the requirements for a corporation to elect S corporation status under IRC § 1362?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
output = model.generate(input_ids, max_new_tokens=512)
print(tokenizer.decode(output[0][input_ids.shape[-1]:], skip_special_tokens=True))

The models were fine-tuned and evaluated using a hybrid RAG pipeline with rule-based section forcing, code-computed tax calculations, disambiguation chunks for complex statutes, and an agentic self-correction loop. Evaluated on complex tax scenarios including SSTB phase-outs, passive loss exceptions, and nonqualified use proration.

Limitations

Trained on synthetic data; not a substitute for professional tax advice
Coverage is focused on U.S. federal tax law

Downloads last month: 12

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for DJLougen/granite4-tax

Base model

ibm-granite/granite-4.0-tiny-base-preview

Finetuned

ibm-granite/granite-4.0-tiny-preview

Adapter

(1)

this model