Instructions to use mrplexar/PortfolioLLM-RAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrplexar/PortfolioLLM-RAG with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mrplexar/PortfolioLLM-RAG")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrplexar/PortfolioLLM-RAG")
model = AutoModelForCausalLM.from_pretrained("mrplexar/PortfolioLLM-RAG", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mrplexar/PortfolioLLM-RAG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrplexar/PortfolioLLM-RAG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrplexar/PortfolioLLM-RAG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mrplexar/PortfolioLLM-RAG

SGLang

How to use mrplexar/PortfolioLLM-RAG with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mrplexar/PortfolioLLM-RAG" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrplexar/PortfolioLLM-RAG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mrplexar/PortfolioLLM-RAG" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrplexar/PortfolioLLM-RAG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mrplexar/PortfolioLLM-RAG with Docker Model Runner:
```
docker model run hf.co/mrplexar/PortfolioLLM-RAG
```

PortfolioLLM-RAG

File size: 1,102 Bytes

277d113

---

license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-360M-Instruct
tags:
- text-generation-inference
- transformers
- smollm2
- portfolio-agent
- roleplay
- gappu
---


# 🌌 PortfolioLLM-RAG (GAPPU AI)

**GAPPU** (Goddess-infused Advanced Portrayal and Presentation Unit) is a specialized fine-tuned model based on **SmolLM2-360M-Instruct**. 
It is designed to serve as a divine and graceful AI assistant for Arpit Ramesan's portfolio.

## 🌟 Model Details
- **Architecture**: SmolLM2
- **Parameters**: 360M
- **Fine-tuning Technique**: QLoRA (4-bit quantization)
- **Primary Function**: Portfolio Assistant / Conversational Agent
- **Personality**: Elegant, Serene, Highly Intelligent
- **Regional Context**: Thalassery, Kerala, India

## 🚀 Usage
This model is intended to be used via the Hugging Face Inference API or integrated into the GAPPU Chat interface.

## 🛠️ Training
The model was fine-tuned on a curated dataset of Arpit Ramesan's professional achievements, research publications, and creative works, augmented with a "divine flowery" persona.