---

language:

• en

license: apache-2.0

base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit

tags:

• legal
• indian-law
• BNS
• BNSS
• BSA
• criminal-law
• qwen
• qwen2.5
• gguf
• llama.cpp
• ollama
• qlora
• unsloth
• domain-adaptation
• instruction-tuning
• question-answering
• law
• india

datasets:

• GSMS-B/Indian-Legal-QA-BNS-BNSS-BSA

pipeline_tag: text-generation

---

⚖️🐉 Indian Legal Qwen 2.5 — 3B (GGUF)

<p align="center">

<img src="https://img.shields.io/badge/Base%20Model-Qwen%202.5%203B-6366F1?style=for-the-badge" alt="Base Model"/>

<img src="https://img.shields.io/badge/Type-GGUF%20Quantized-A855F7?style=for-the-badge" alt="Type"/>

<img src="https://img.shields.io/badge/Domain-Indian%20Criminal%20Law-DC2626?style=for-the-badge" alt="Domain"/>

<img src="https://img.shields.io/badge/Method-QLoRA-2563EB?style=for-the-badge" alt="Method"/>

<img src="https://img.shields.io/badge/Acts-BNS%20%7C%20BNSS%20%7C%20BSA-16A34A?style=for-the-badge" alt="Acts"/>

<img src="https://img.shields.io/badge/License-Apache%202.0-F59E0B?style=for-the-badge" alt="License"/>

</p>

> 🟡 This is the GGUF-quantized version — for CPU inference via Ollama or llama.cpp. For full-precision inference see the Merged Model · For lightweight adapter loading see the Adapter.

---

📖 Model Description

Indian Legal Qwen 2.5 — 3B (GGUF) is a quantized, CPU-friendly version of GSMS-B/Indian-Legal-Qwen2.5-3B, a domain-adapted model fine-tuned using QLoRA on a structured question-answer dataset covering all 1,059 sections of India's three landmark 2023 criminal justice reform acts:

| 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 — giving it broad, structured coverage of India's reformed criminal law framework. This GGUF build lets you run the model without a GPU, using llama.cpp or Ollama.

---

🔗 Model Family — Qwen 2.5 3B

| Variant | Repo | Best For |

|---|---|---|

| 🟢 Merged | GSMS-B/Indian-Legal-Qwen2.5-3B | Out-of-the-box inference, Gradio / API deployment |

| 🔵 LoRA Adapter | GSMS-B/Indian-Legal-Qwen2.5-3B-Adapter | Lightweight loading on top of base model |

| 🟡 GGUF (this repo) | GSMS-B/Indian-Legal-Qwen2.5-3B-GGUF | CPU inference via Ollama / llama.cpp |

---

🚀 Quick Start

💻 Run with Ollama

ollama run hf.co/GSMS-B/Indian-Legal-Qwen2.5-3B-GGUF

⚙️ Run with llama.cpp

./llama-cli \
  -hf GSMS-B/Indian-Legal-Qwen2.5-3B-GGUF \
  -p "What is a Zero FIR under BNSS 2023?" \
  -n 300 \
  --temp 0.1

🐍 Run with llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="GSMS-B/Indian-Legal-Qwen2.5-3B-GGUF",
    filename="*.gguf",
)

SYSTEM = "You are an expert legal assistant specializing in Indian criminal law — BNS, BNSS, and BSA 2023."

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": SYSTEM},
        {"role": "user", "content": "What is a Zero FIR under BNSS 2023?"}
    ],
    temperature=0.1,
    max_tokens=300
)

print(response["choices"][0]["message"]["content"])

---

🎯 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

| 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 |

| 📚 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 |

| 💻 Offline / Edge Deployment | Run on consumer CPUs without a GPU — ideal for local apps, kiosks, or low-resource environments |

| 📝 Structured Legal Summarization | Summarize individual sections when the section text is supplied as input context |

| 🏛️ Legal NLP Research | Benchmark Indian criminal law understanding across model families (Qwen vs Llama) |

| ⚖️ Comparative Law Analysis | Highlight differences between old acts (IPC/CrPC/IEA) and their 2023 replacements |

❌ 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

| Property | Value |

|---|---|

| 🤖 Base model | unsloth/Qwen2.5-3B-Instruct-bnb-4bit |

| 🔧 Fine-tuning method | QLoRA |

| 🎛️ LoRA rank | 16 |

| 🎛️ LoRA alpha | 16 |

| 🧩 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 (per device) | 2 |

| 📈 Learning rate | 2e-4 |

| ⚙️ Optimizer | adamw_8bit |

| 💻 Hardware | Google Colab T4 GPU |

| 🛠️ Framework | Unsloth + TRL SFTTrainer |

| 💬 Prompt format | ChatML |

| 🗜️ Quantization | GGUF (converted from merged FP16 model) |

---

📊 Training Dataset

| 📂 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.