ProfRutPatel/geopolitics-india-qwen2.5-0.5b-lora

Geopolitics India - Qwen2.5-0.5B LoRA Adapter

Fine-tuned Qwen2.5-0.5B-Instruct on Global Geopolitical Challenges and India's Response using 4-bit QLoRA on an NVIDIA RTX 3050.

Training Details

Parameter	Value
Base model	Qwen/Qwen2.5-0.5B-Instruct (500M params)
Method	QLoRA (LoRA r=16, alpha=32, NF4 4-bit)
Trainable params	1,081,344 / 495M (0.22%)
Epochs	3
GPU	NVIDIA RTX 3050 Laptop
Training time	48 seconds
Final train loss	3.027
Token accuracy	49.4%

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("ProfRutPatel/geopolitics-india-qwen2.5-0.5b-lora")
model = PeftModel.from_pretrained(base, "ProfRutPatel/geopolitics-india-qwen2.5-0.5b-lora")

messages = [{"role": "user", "content": "What are India's key geopolitical challenges?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors='pt')
out = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Sample Output

India faces strategic dependencies in the Indian Ocean, regional security tensions, cybersecurity threats, growing Middle East influence disputes, resource management challenges, and serious climate change impacts on its economy and infrastructure.