GSMS-B

Indian-Legal-Llama-3.2-3B-Adapter

README

License: apache-2.0

📖 Model Description

Indian Legal Llama 3.2 — 3B (LoRA Adapter) contains the QLoRA adapter weights trained on top of unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit, domain-adapted for all 1,059 sections of India's three landmark 2023 criminal justice reform acts:

Table with columns: Act, Full Name, Replaces, Sections
Act	Full Name	Replaces	Sections
📕 BNS 2023	Bharatiya Nyaya Sanhita	IPC 1860	358
📗 BNSS 2023	Bharatiya Nagarik Suraksha Sanhita	CrPC 1973	531
📘 BSA 2023	Bharatiya Sakshya Adhiniyam	Indian Evidence Act 1872	170

Trained on 6,354 instruction-format QA pairs — 6 question types per section covering definitions, scenarios, legal elements, exceptions, and consequences.

🔗 Model Family — Llama 3.2 3B

Table with columns: Variant, Repo, Best For
Variant	Repo	Best For
🟢 Merged	GSMS-B/Indian-Legal-Llama-3.2-3B	Out-of-the-box inference, Gradio / API deployment
🔵 LoRA Adapter (this repo)	`GSMS-B/Indian-Legal-Llama-3.2-3B-Adapter`	Lightweight loading on top of base model
🟡 GGUF (Quantized)	GSMS-B/Indian-Legal-Llama-3.2-3B-GGUF	CPU inference via Ollama / llama.cpp

🚀 Quick Start

python

from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch base_model_id = "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit"adapter_id    = "GSMS-B/Indian-Legal-Llama-3.2-3B-Adapter" tokenizer = AutoTokenizer.from_pretrained(base_model_id)base_model = AutoModelForCausalLM.from_pretrained(    base_model_id,    torch_dtype=torch.float16,    device_map="auto")model = PeftModel.from_pretrained(base_model, adapter_id) SYSTEM = "You are an expert legal assistant specializing in Indian criminal law — BNS, BNSS, and BSA 2023." def ask(question):    messages = [        {"role": "system", "content": SYSTEM},        {"role": "user",   "content": question}    ]    text   = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)    inputs = tokenizer(text, return_tensors="pt").to(model.device)    with torch.no_grad():        out = model.generate(**inputs, max_new_tokens=300, temperature=0.1,                             do_sample=True, pad_token_id=tokenizer.eos_token_id)    return tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) print(ask("What are the key differences between BNS 2023 and IPC 1860?"))

🎯 Recommended Use Cases

⚠️ Important Note: This model has been domain-adapted on structured QA data and works best as a component in a larger pipeline rather than a standalone answer engine. Direct usage without retrieval context may produce incomplete or imprecise answers on complex legal queries.

✅ Where this model excels

Table with columns: Use Case, 💡 How to Use
Use Case	💡 How to Use
🔍 RAG Pipeline	Pair with a BM25 or vector retriever over BNS/BNSS/BSA texts; feed retrieved sections as context for grounded, citation-backed answers
🤖 Legal Chatbot Backend	Use as the generation backbone of a legal assistant app with a ChromaDB / FAISS document store
🧩 Flexible Adapter Stacking	Swap this adapter onto the base model without maintaining a full merged checkpoint — ideal for multi-adapter experiments
📚 Legal Education Tool	Build interactive Q&A apps for law students and practitioners learning the 2023 criminal justice reforms
🔎 Section Lookup Assistant	Combine with a section index to surface the exact BNS / BNSS / BSA provision relevant to a given situation
🧪 Further Fine-tuning	Use as a starting point for more specialised adaptation (e.g., only BNSS procedure, only BSA evidence rules)

❌ Not recommended for

Standalone legal advice without a retrieval component
High-stakes legal decisions without qualified human review
Jurisdictions or acts outside BNS / BNSS / BSA 2023

🏋️ Training Details

Table with columns: Property, Value
Property	Value
🤖 Base model	`unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit`
🔧 Fine-tuning method	QLoRA
🎛️ LoRA rank	64
🎛️ LoRA alpha	128
🧩 Target modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
📊 Training data	6,354 QA pairs — 1,059 sections × 6 question types
🔁 Epochs	3
📦 Batch size (effective)	4

📊 Training Dataset

Table with columns: 📂 Dataset, 🔗 Link
📂 Dataset	🔗 Link
Indian Legal QA — BNS + BNSS + BSA 2023	GSMS-B/Indian-Legal-QA-BNS-BNSS-BSA

6 question types per section: definitional_topic · definitional_section · scenario · elements · exceptions · consequence

👤 Author

GSMS-B — Bugatha Ganasyam Mani Sankar 🤗 Hugging Face Profile

⚠️ Disclaimer

This model is intended for research and educational purposes only. It does not constitute legal advice. Outputs should not be relied upon for any legal decision without review by a qualified legal professional. The model's responses reflect patterns in training data and may contain errors or omissions.

⚡ Fine-tuned using Unsloth for training efficiency.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

GSMS-B

Model Tree

Base

meta-llama/Llama-3.2-3B-Instruct

Adapter

this model

Input Modalities

Text

Output Modalities