metadata
language:
- fr
- en
license: apache-2.0
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:
- merged
- lora
- peft
- qwen2
- cybersecurity
- fine-tuned
model-index:
- name: RGPD-Expert-1.5B-Merged
results: []
RGPD-Expert-1.5B — Merged (Standalone)
Expert en RGPD (Reglement General sur la Protection des Donnees)
This is the merged / standalone version of AYI-NEDJIMI/RGPD-Expert-1.5B. The LoRA adapter weights have been fully merged into the base model (Qwen/Qwen2.5-1.5B-Instruct), so no PEFT library is required at inference time.
| Property | Value |
|---|---|
| Base model | Qwen/Qwen2.5-1.5B-Instruct |
| Adapter version | AYI-NEDJIMI/RGPD-Expert-1.5B |
| Parameters | 1.5B |
| LoRA rank (r) | 64 |
| LoRA alpha | 128 |
| Precision | float16 |
| License | Apache 2.0 |
Description
- FR : Expert en RGPD (Reglement General sur la Protection des Donnees). Version fusionnee — chargement direct sans adaptateur PEFT.
- EN : GDPR (General Data Protection Regulation) expert. Merged version — direct loading without PEFT adapter.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "AYI-NEDJIMI/RGPD-Expert-1.5B-Merged"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain the key principles of GDPR/RGPD."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Note: No need to install or import
peft— this model is fully standalone.
Links
- Adapter version (LoRA): AYI-NEDJIMI/RGPD-Expert-1.5B
- Base model: Qwen/Qwen2.5-1.5B-Instruct
- Portfolio collection: AYI-NEDJIMI Collections
Training details
This model was fine-tuned using LoRA (Low-Rank Adaptation) with the following configuration:
- LoRA rank (r): 64
- LoRA alpha: 128
- LoRA dropout: 0.05
- Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
The adapter weights were then merged into the base model using model.merge_and_unload() from the PEFT library to produce this standalone checkpoint.