Instructions to use goasty/Qwen3-4B-Indian-Law with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use goasty/Qwen3-4B-Indian-Law with Transformers:

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

pipe = pipeline("text-generation", model="goasty/Qwen3-4B-Indian-Law")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("goasty/Qwen3-4B-Indian-Law")
model = AutoModelForMultimodalLM.from_pretrained("goasty/Qwen3-4B-Indian-Law")
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 goasty/Qwen3-4B-Indian-Law with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "goasty/Qwen3-4B-Indian-Law"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "goasty/Qwen3-4B-Indian-Law",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/goasty/Qwen3-4B-Indian-Law

SGLang

How to use goasty/Qwen3-4B-Indian-Law 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 "goasty/Qwen3-4B-Indian-Law" \
    --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": "goasty/Qwen3-4B-Indian-Law",
		"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 "goasty/Qwen3-4B-Indian-Law" \
        --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": "goasty/Qwen3-4B-Indian-Law",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use goasty/Qwen3-4B-Indian-Law 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 goasty/Qwen3-4B-Indian-Law 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 goasty/Qwen3-4B-Indian-Law to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for goasty/Qwen3-4B-Indian-Law to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="goasty/Qwen3-4B-Indian-Law",
    max_seq_length=2048,
)

Docker Model Runner
How to use goasty/Qwen3-4B-Indian-Law with Docker Model Runner:
```
docker model run hf.co/goasty/Qwen3-4B-Indian-Law
```

Qwen3-4B Indian Law

A domain-adapted legal assistant fine-tuned from Qwen3-4B on a large corpus of Indian legal texts, statutory provisions, constitutional law, criminal law, evidence law, procedural law, and court judgments.

The model is designed to assist with:

Indian legal question answering
Statutory interpretation
Constitution-related queries
Criminal law and procedure
Legal reasoning
Case law understanding
Legal research assistance
Judgment summarization
Legal education and training

Model Overview

Item	Value
Base Model	unsloth/Qwen3-4B
Fine-Tuning Method	LoRA + QLoRA
Framework	Unsloth
Context Length	4096
Precision	BF16
LoRA Rank	32
LoRA Alpha	32
Optimizer	AdamW 8-bit
Learning Rate	2e-4
Scheduler	Cosine
Epochs	2
Effective Batch Size	32
Domain	Indian Legal Knowledge

Training Dataset

The training corpus was created by combining multiple publicly available Indian legal datasets together with a large judgment corpus.

The objective was to expose the model to:

Legal question answering
Statutory provisions
Constitutional law
Criminal law
Procedural law
Evidence law
Court judgments
Legal summarization
Legal reasoning

Dataset Composition

1. Indian Legal Supervised Fine-Tuning Dataset

Source:

Prarabdha/indian-legal-supervised-fine-tuning-data

Characteristics:

Large-scale legal instruction dataset
Context → Question → Answer format
Derived from Indian court judgments
Designed for legal reasoning and legal QA

Original Size:

6,055,371 samples

To prevent over-representation and memorization, a subset was selected during dataset balancing.

Contribution:

≈ 250,000 samples

Example:

Context:
Delhi Development Authority v. Kanwar Kumar Mehta

Question:
Was the High Court justified in calculating interest on escalation charges?

Answer:
Yes. The High Court's decision was held justified on equitable grounds.

2. Indian Law Instruction Dataset

Source:

viber1/indian-law-dataset

Characteristics:

Legal instruction-response pairs
Covers Indian legal concepts
General legal knowledge
Legal terminology

Samples:

24,607

Example:

Question:
What is the difference between a petition and a plaint?

Answer:
A petition is a formal request seeking relief, whereas a plaint is the written statement initiating a civil suit.

3. Constitution of India QA Dataset

Custom processed dataset containing question-answer pairs generated from constitutional provisions.

Coverage:

Fundamental Rights
Directive Principles
Union and State relations
Parliament
Judiciary
Constitutional amendments

Samples:

4,082

Example:

Question:
What is India according to the Constitution?

Answer:
India, that is Bharat, shall be a Union of States.

4. Indian Penal Code (IPC) Dataset

Custom processed IPC question-answer corpus.

Coverage:

Definitions
Offences
Punishments
Criminal liability
General exceptions

Samples:

2,267

Example:

Question:
What is the title and extent of operation of the Indian Penal Code?

Answer:
The title is the Indian Penal Code and it extends to offences committed within India and certain offences committed outside India.

5. Code of Criminal Procedure (CrPC) Dataset

Custom processed question-answer dataset generated from CrPC provisions.

Coverage:

Investigation
Arrest
Bail
Trial procedures
Appeals
Criminal courts

Samples:

8,194

Example:

Question:
What is the short title and commencement of the CrPC?

Answer:
The Code of Criminal Procedure, 1973.

6. IndicLegalQA

Legal question-answer dataset derived from Indian Supreme Court judgments.

Coverage:

Case law
Judicial reasoning
Legal interpretation

Samples:

10,002

Example:

Question:
Who was the respondent in Union of India v. Maj. Gen. Manomoy Ganguly?

Answer:
Maj. Gen. Manomoy Ganguly.

7. Bharatiya Nyaya Sanhita (BNS)

Structured dataset generated from the Bharatiya Nyaya Sanhita, 2023.

Coverage:

Criminal offences
Punishments
Definitions
Modern criminal law provisions

Source Structure:

Chapter
Section
Section Name
Description

8. Bharatiya Sakshya Adhiniyam (BSA)

Structured dataset generated from the Bharatiya Sakshya Adhiniyam, 2023.

Coverage:

Evidence law
Documentary evidence
Digital evidence
Witness testimony

Source Structure:

Chapter
Section
Section Name
Description

9. Indian Court Judgments Corpus

Largest component of the training data.

Sources include:

Supreme Court judgments
High Court judgments
CourtNIC archives
JUDIS archives

Documents processed:

16,726 judgment files

Coverage:

Constitutional law
Civil law
Criminal law
Taxation
Property law
Administrative law
Service law

Training samples were automatically converted into:

Context → Question → Answer

instruction format.

Dataset Balancing

The original corpus was heavily dominated by judgment-derived samples.

Without balancing:

451,756 samples

Distribution:

Judgment-heavy

To improve generalization across statutory and constitutional law, a balancing procedure was applied.

Final balanced dataset:

304,930 samples

Approximate distribution:

Category	Samples
General Legal QA	190,744
Court Judgments	66,368
Constitution	32,346
CrPC	8,719
IPC	6,698
BNS	50
BSA	5

This balancing significantly reduced bias toward judgment memorization while preserving broad legal coverage.

Training Configuration

The model was fine-tuned using LoRA adapters on top of Qwen3-4B.

LoRA Configuration

r=32
lora_alpha=32
lora_dropout=0.0

Target Modules:

q_proj
k_proj
v_proj
o_proj
gate_proj
up_proj
down_proj

Optimization

Learning Rate: 2e-4
Weight Decay: 0.01
Warmup Ratio: 0.03
Scheduler: Cosine
Optimizer: AdamW 8-bit

Training

Epochs: 2
Max Sequence Length: 4096
Batch Size: 8
Gradient Accumulation: 4
Effective Batch Size: 32
Precision: BF16

Example Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "goasty/Qwen3-4B-Indian-Law"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = """
What is Article 21 of the Constitution of India?
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=256
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Intended Use

Suitable for:

Legal research assistance
Educational purposes
Law students
Legal document analysis
Statutory interpretation
Legal Q&A systems
Retrieval-Augmented Generation (RAG)

Limitations

Not a substitute for licensed legal counsel.
May generate legally incorrect or outdated interpretations.
Should not be relied upon for litigation or legal advice without expert review.
Training data contains historical judgments and statutes which may have been amended or overruled.

Acknowledgements

This work builds upon:

Qwen Team
Unsloth
Hugging Face Datasets Community
Indian Legal Open Data Contributors
Supreme Court and High Court public legal records

Citation

@misc{qwen3_indian_law,
  title={Qwen3-4B Indian Law},
  author={Aditya},
  year={2026},
  note={Fine-tuned Qwen3-4B model for Indian legal reasoning and question answering}
}

Downloads last month: 36

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for goasty/Qwen3-4B-Indian-Law

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

unsloth/Qwen3-4B

Adapter

(25)

this model

goasty
/

Qwen3-4B-Indian-Law

Qwen3-4B Indian Law

Model Overview

Training Dataset

Dataset Composition

1. Indian Legal Supervised Fine-Tuning Dataset

2. Indian Law Instruction Dataset

3. Constitution of India QA Dataset

4. Indian Penal Code (IPC) Dataset

5. Code of Criminal Procedure (CrPC) Dataset

6. IndicLegalQA

7. Bharatiya Nyaya Sanhita (BNS)

8. Bharatiya Sakshya Adhiniyam (BSA)

9. Indian Court Judgments Corpus

Dataset Balancing

Training Configuration

LoRA Configuration

Optimization

Training

Example Usage

Intended Use

Limitations

Acknowledgements

Citation

Model tree for goasty/Qwen3-4B-Indian-Law

Datasets used to train goasty/Qwen3-4B-Indian-Law