RGPD-Expert-1.5B-GGUF

GGUF quantized versions of AYI-NEDJIMI/RGPD-Expert-1.5B for use with Ollama, llama.cpp, LM Studio, and other GGUF-compatible inference engines.

Model Description

This is a fine-tuned Qwen2.5-1.5B-Instruct model specialized in RGPD/GDPR data protection regulation. It can answer questions about GDPR compliance, data subject rights, data processing agreements, privacy impact assessments, and regulatory requirements in both French and English.

Part of the AYI-NEDJIMI Cybersecurity AI Portfolio:

• AYI-NEDJIMI/CyberSec-AI-Portfolio — Full collection

Available Quantizations

Filename	Quant Type	Size	Description
rgpd-expert-1.5b-Q4_K_M.gguf	Q4_K_M	941 MB	Recommended — Best balance of quality and size (~33% of F16)
rgpd-expert-1.5b-Q5_K_M.gguf	Q5_K_M	1.07 GB	Higher quality, slightly larger (~38% of F16)
rgpd-expert-1.5b-Q8_0.gguf	Q8_0	1.57 GB	Near-lossless quantization (~54% of F16)

Quantization Format Details

• Q4_K_M: 4-bit quantization with k-quant medium quality. Excellent for resource-constrained environments. Minimal quality loss for most tasks.
• Q5_K_M: 5-bit quantization with k-quant medium quality. Good middle ground between Q4 and Q8.
• Q8_0: 8-bit quantization. Near-original quality with ~50% size reduction from F16.

How to Use

Ollama

Create a Modelfile:

FROM ./rgpd-expert-1.5b-Q4_K_M.gguf

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

SYSTEM "You are a RGPD/GDPR expert assistant. You provide detailed, accurate guidance on data protection regulation, privacy rights, GDPR compliance, and data processing requirements. You respond in the same language as the user's question."

PARAMETER temperature 0.7
PARAMETER top_p 0.8
PARAMETER top_k 20
PARAMETER stop "<|im_end|>"

Then run:

ollama create rgpd-expert -f Modelfile
ollama run rgpd-expert

llama.cpp

# Interactive chat
./llama-cli -m rgpd-expert-1.5b-Q4_K_M.gguf \
  -p "You are a RGPD/GDPR expert assistant." \
  --chat-template chatml \
  -cnv

# Server mode
./llama-server -m rgpd-expert-1.5b-Q4_K_M.gguf \
  --host 0.0.0.0 --port 8080

LM Studio

1. Download the desired GGUF file
2. Open LM Studio and load the model from your downloads
3. Select the ChatML chat template
4. Set the system prompt to: "You are a RGPD/GDPR expert assistant."
5. Start chatting!

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(model_path="rgpd-expert-1.5b-Q4_K_M.gguf", n_ctx=4096)

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are a RGPD/GDPR expert assistant."},
        {"role": "user", "content": "Quels sont les droits des personnes concernées selon le RGPD?"}
    ],
    temperature=0.7,
    top_p=0.8,
    top_k=20,
)
print(response["choices"][0]["message"]["content"])

Related Models

Version	Link
Merged (SafeTensors)	AYI-NEDJIMI/RGPD-Expert-1.5B
LoRA Adapter	AYI-NEDJIMI/RGPD-Expert-1.5B-Adapter
GGUF (this repo)	AYI-NEDJIMI/RGPD-Expert-1.5B-GGUF
Portfolio Collection	AYI-NEDJIMI/CyberSec-AI-Portfolio

Technical Details

• Base Model: Qwen/Qwen2.5-1.5B-Instruct
• Fine-tuning: QLoRA (4-bit) with LoRA adapters merged back
• Architecture: Qwen2ForCausalLM
• Context Length: 4096 tokens
• Chat Template: ChatML
• Converted with: llama.cpp (convert_hf_to_gguf.py)