GoldenNet-Qwen2.5-0.5B-Full-v1/README.md

license, language, base_model, tags, datasets, pipeline_tag, library_name, model-index

license	language	base_model	tags	datasets	pipeline_tag	library_name	model-index
apache-2.0	ar en	Qwen/Qwen2.5-0.5B-Instruct	qwen2 arabic iraqi government classification ner fine-tuned full-finetune goldennet	custom	text-generation	transformers	name results GoldenNet-Qwen2.5-0.5B-Full-v1 task metrics type name text-classification Document Classification type value name loss 0.3636 Eval Loss

GoldenNet-Qwen2.5-0.5B-Full-v1

Model Description

GoldenNet-Qwen2.5-0.5B-Full-v1 is a fully fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct specialized for Iraqi Government Correspondence Processing.

This is the full fine-tuning variant where all 494M parameters were trained, potentially offering the best task-specific performance.

Tasks

1. Document Classification - 8 categories (طلب، شكوى، تقرير، إعلام، استفسار، دعوة، تعميم، إحالة)
2. Named Entity Recognition - Extracts persons, organizations, locations, dates, monetary values, laws

Model Comparison

Model	Method	Train Loss	Eval Loss	Training Time	Size
QLoRA-v1	4-bit QLoRA	0.448	0.2998	49s	943MB
LoRA-v1	Standard LoRA	0.496	0.3665	70s	943MB
Full-v1	Full Fine-tune	0.461	0.3636	121s	1.9GB

Training Details

Parameter	Value
Base Model	Qwen/Qwen2.5-0.5B-Instruct
Fine-tuning Method	Full (all parameters)
Learning Rate	5e-5
Optimizer	AdamW 8-bit
Epochs	3
Batch Size	1 (effective: 16)
Max Sequence Length	1024
Precision	BF16
Trainable Parameters	494M (100%)
Hardware	NVIDIA RTX 5070 (8GB VRAM)

Loss Progression

• Epoch 1: 0.983
• Epoch 2: 0.328
• Epoch 3: 0.171 (lowest among all variants!)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Alamori/GoldenNet-Qwen2.5-0.5B-Full-v1",
    device_map="auto",
    torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Alamori/GoldenNet-Qwen2.5-0.5B-Full-v1")

# Classification example
correspondence = """جمهورية العراق
وزارة التربية
العدد: 1234/ت/2025

إلى/ السيد مدير عام التعليم المحترم

م/ طلب تعيين معلمين

نرجو الموافقة على تعيين 50 معلماً.

مع التقدير"""

instruction = "صنّف المراسلة الحكومية التالية إلى إحدى الفئات: طلب، شكوى، تقرير، إعلام، استفسار، دعوة، تعميم، إحالة. أجب بصيغة JSON."

messages = [{"role": "user", "content": f"{instruction}\n\n{correspondence}"}]
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=256, temperature=0.1)
print(tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True))

When to Use This Model

• Use Full-v1 when you need maximum task-specific performance and have sufficient storage/memory
• Use QLoRA-v1 for best balance of quality and efficiency (recommended for most cases)
• Use LoRA-v1 for comparison or when you need standard LoRA compatibility

Related Models

• GoldenNet-Qwen2.5-0.5B-QLoRA-v1 - 4-bit quantized (best eval loss)
• GoldenNet-Qwen2.5-0.5B-LoRA-v1 - Standard LoRA

License

Apache 2.0

---

Developed by Golden Net AI
Empowering Iraqi Government Digital Transformation