--- language: - en license: apache-2.0 base_model: unsloth/Qwen2.5-1.5B-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 --- # โš–๏ธ๐Ÿ‰ Indian Legal Qwen 2.5 โ€” 1.5B (GGUF)

Base Model Type Domain Method Acts License

> ๐ŸŸก **This is the GGUF-quantized version** โ€” for CPU inference via Ollama or llama.cpp. For full-precision inference see the [Merged Model](https://huggingface.co/GSMS-B/Indian-Legal-Qwen2.5-1.5B) ยท For lightweight adapter loading see the [Adapter](https://huggingface.co/GSMS-B/Indian-Legal-Qwen2.5-1.5B-Adapter). --- ## ๐Ÿ“– Model Description **Indian Legal Qwen 2.5 โ€” 1.5B (GGUF)** is a quantized, CPU-friendly version of [`GSMS-B/Indian-Legal-Qwen2.5-1.5B`](https://huggingface.co/GSMS-B/Indian-Legal-Qwen2.5-1.5B), 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 | |---|---|---|---| | ๐Ÿ“• **BNS 2023** | Bharatiya Nyaya Sanhita | IPC 1860 | 358 | | ๐Ÿ“— **BNSS 2023** | Bharatiya Nagarik Suraksha Sanhita | CrPC 1973 | 531 | | ๐Ÿ“˜ **BSA 2023** | Bharatiya Sakshya Adhiniyam | Indian Evidence Act 1872 | 170 | Trained on **6,354 instruction-format QA pairs** โ€” 6 question types per section covering definitions, scenarios, legal elements, exceptions, and consequences โ€” giving it broad, structured coverage of India's reformed criminal law framework. As the smallest model in the family, this GGUF build is ideal for fast, fully offline CPU inference. --- ## ๐Ÿ”— Model Family โ€” Qwen 2.5 1.5B | Variant | Repo | Best For | |---|---|---| | ๐ŸŸข **Merged** | [GSMS-B/Indian-Legal-Qwen2.5-1.5B](https://huggingface.co/GSMS-B/Indian-Legal-Qwen2.5-1.5B) | Out-of-the-box inference, Gradio / API deployment | | ๐Ÿ”ต **LoRA Adapter** | [GSMS-B/Indian-Legal-Qwen2.5-1.5B-Adapter](https://huggingface.co/GSMS-B/Indian-Legal-Qwen2.5-1.5B-Adapter) | Lightweight loading on top of base model | | ๐ŸŸก **GGUF (this repo)** | `GSMS-B/Indian-Legal-Qwen2.5-1.5B-GGUF` | CPU inference via Ollama / llama.cpp | --- ## ๐Ÿš€ Quick Start ### ๐Ÿ’ป Run with Ollama ```bash ollama run hf.co/GSMS-B/Indian-Legal-Qwen2.5-1.5B-GGUF ``` ### โš™๏ธ Run with llama.cpp ```bash ./llama-cli \ -hf GSMS-B/Indian-Legal-Qwen2.5-1.5B-GGUF \ -p "What is a Zero FIR under BNSS 2023?" \ -n 300 \ --temp 0.1 ``` ### ๐Ÿ Run with llama-cpp-python ```python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="GSMS-B/Indian-Legal-Qwen2.5-1.5B-GGUF", filename="*.gguf", ) SYSTEM = "You are an expert legal assistant specializing in Indian criminal law โ€” 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"]) ``` --- ## ๐ŸŽฏ Recommended Use Cases > โš ๏ธ **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. ### โœ… Where this model excels | Use Case | ๐Ÿ’ก How to Use | |---|---| | ๐Ÿ” **RAG Pipeline** | Pair with a BM25 or vector retriever over BNS/BNSS/BSA texts; feed retrieved sections as context for grounded, citation-backed answers | | ๐Ÿค– **Legal Chatbot Backend** | Use as the generation backbone of a legal assistant app with a ChromaDB / FAISS document store | | ๐Ÿ“š **Legal Education Tool** | Build interactive Q&A apps for law students and practitioners learning the 2023 criminal justice reforms | | ๐Ÿ”Ž **Section Lookup Assistant** | Combine with a section index to surface the exact BNS / BNSS / BSA provision relevant to a given situation | | ๐Ÿ’ป **Offline / Edge Deployment** | Smallest model in the family, runnable on consumer CPUs without a GPU โ€” ideal for local apps, kiosks, or low-resource environments | | ๐Ÿ“ **Structured Legal Summarization** | Summarize individual sections when the section text is supplied as input context | | ๐Ÿ›๏ธ **Legal NLP Research** | Benchmark Indian criminal law understanding across model families (Qwen vs Llama) | | โš–๏ธ **Comparative Law Analysis** | Highlight differences between old acts (IPC/CrPC/IEA) and their 2023 replacements | ### โŒ 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 --- ## ๐Ÿ‹๏ธ Training Details | Property | Value | |---|---| | ๐Ÿค– Base model | `unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit` | | ๐Ÿ”ง Fine-tuning method | QLoRA | | ๐ŸŽ›๏ธ LoRA rank | 64 | | ๐ŸŽ›๏ธ LoRA alpha | 128 | | ๐Ÿงฉ Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj | | ๐Ÿ“Š Training data | 6,354 QA pairs โ€” 1,059 sections ร— 6 question types | | ๐Ÿ” Epochs | 3 | | ๐Ÿ“ฆ Batch size (per device) | 4 | | ๐Ÿ“ˆ Learning rate | 2e-4 | | โš™๏ธ Optimizer | adamw_8bit | | ๐Ÿ’ป Hardware | Google Colab T4 GPU | | ๐Ÿ› ๏ธ Framework | Unsloth + TRL SFTTrainer | | ๐Ÿ’ฌ Prompt format | ChatML | | ๐Ÿ—œ๏ธ Quantization | GGUF (converted from merged FP16 model) | --- ## ๐Ÿ“Š Training Dataset | ๐Ÿ“‚ Dataset | ๐Ÿ”— Link | |---|---| | Indian Legal QA โ€” BNS + BNSS + BSA 2023 | [GSMS-B/Indian-Legal-QA-BNS-BNSS-BSA](https://huggingface.co/datasets/GSMS-B/Indian-Legal-QA-BNS-BNSS-BSA) | **6 question types per section:** `definitional_topic` ยท `definitional_section` ยท `scenario` ยท `elements` ยท `exceptions` ยท `consequence` --- ## ๐Ÿ‘ค Author **GSMS-B** โ€” Bugatha Ganasyam Mani Sankar ๐Ÿค— [Hugging Face Profile](https://huggingface.co/GSMS-B) --- ## โš ๏ธ 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. --- *โšก Fine-tuned using [Unsloth](https://github.com/unslothai/unsloth) for training efficiency.*