Deepseek_ID_Legal_Preview_GGUF

📧 Github 🔗 LinkedIn

🧠 DeepSeek-R1-0528-Qwen3-8B Instruct Fine-Tuned with GRPO on Indonesian Legal QA Dataset

Welcome! This repository hosts a fine-tuned version of DeepSeek-R1-0528-Qwen3-8B using Group Relative Policy Optimization (GRPO), trained on a custom Indonesian Legal Q&A Dataset. The goal is to enhance the model's reasoning and structured thinking capabilities for legal question-answering tasks. You can try the demo here

---

🚀 Model Summary

• Purpose: Research and Development
• Base Model: DeepSeek-R1-0528-Qwen3-8B
• Language: Bahasa Indonesia 🇮🇩
• Domain: Legal / Law (Q&A format)
• Purpose: Boost performance in structured, legal reasoning under Indonesian legal context

---

🏋️ Training Summary

• Fine-tuning Method: Group Relative Policy Optimization (GRPO) combined with Knowledge Distillation
• Pipeline: Cloud to Cloud training
• Dataset: Indonesian Legal Questions and Answers pertanyaan hukum
• Compute: Nvidia RTX6000 Ada
• Provider: vast.ai
• Training Steps: 2000
• Number of Generation: 16
• Cost: 50 USD
• Distilled Knowledge: DeepSeek_0528_8B_Legal_Distill

---

🧩 What is GRPO?

Group Relative Policy Optimization (GRPO) is an advanced reinforcement learning fine-tuning technique that:

• Groups samples by difficulty or topic (e.g., legal concepts)
• Encourages policies (model outputs) to optimize within their group context
• Promotes structured and relative improvements, not just raw accuracy

This method leads to:

• Better structured answers
• Improved logical flow
• Greater consistency in domain-specific reasoning (e.g., answering legal queries with relevant laws and regulations)

---

🧠 Structured Thinking Enabled

The fine-tuned model is trained to think in steps using GRPO:

1. Understand the legal context
2. Identify the relevant law
3. Apply reasoning with facts
4. Summarize the legal conclusion clearly

This mimics how law students or practitioners approach legal cases, making the model suitable for:

• Law education
• Legal chatbot assistants
• Indonesian legal exam prep

---

🗂️ Supported Software (No Coding Required)

You can use the GGUF version directly with these tools:

• LM Studio – Desktop app (Windows/Mac) with chat interface and model downloader
• Ollama – Simple local model runner with ollama run commands (Mac/Linux/Windows WSL)
• KoboldCPP – For storytelling and roleplay, runs entirely on CPU or GPU
• text-generation-webui – Web UI for running GGUF models with extensive settings
• Jan – Cross‑platform AI desktop app with offline support
• GPT4All – Desktop UI with GGUF compatibility for quick model loading

---

💻 How to Use

1. Download the GGUF file from the “Files and Versions” tab of this model page.
2. Open your preferred software (e.g., LM Studio, Ollama, KoboldCPP).
3. Load or import the GGUF file.
4. Customize system prompt

Anda adalah asisten AI yang ahli di bidang hukum Indonesia. Anda dapat membantu konsultasi hukum, menjawab pertanyaan, dan memberikan analisis berdasarkan peraturan perundang-undangan yang relevan.
Untuk setiap respons, Anda harus berfikir dan menjawab dengan Bahasa Indonesia, serta gunakan format:
<think>
...
</think>
Tuliskan jawaban akhir secara jelas, ringkas, profesional, dan berempati jika diperlukan. Gunakan bahasa hukum yang mudah dipahami. Sertakan referensi hukum Indonesia yang relevan. Selalu rekomendasikan konsultasi dengan ahli hukum untuk keputusan final.

1. Start chatting with the model — no Python code required!

Adakah hukumnya yang mengatur pembagian persentase/laba dalam mendirikan suatu perusahaan?
Dan berapa persenkah yang didapat oleh si pemilik ide untuk mendirikan perusahaan,
jika dia tidak menyetor modal sedikit pun atau hanya menjalankan saja?

---

🤝 Acknowledgements

• Deepseek team
• GRPO research paper

---