Instructions to use Anupb7/anup-personal-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anupb7/anup-personal-llm with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "Anupb7/anup-personal-llm")

Transformers

How to use Anupb7/anup-personal-llm with Transformers:

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

pipe = pipeline("text-generation", model="Anupb7/anup-personal-llm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Anupb7/anup-personal-llm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Anupb7/anup-personal-llm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Anupb7/anup-personal-llm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Anupb7/anup-personal-llm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Anupb7/anup-personal-llm

SGLang

How to use Anupb7/anup-personal-llm 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 "Anupb7/anup-personal-llm" \
    --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": "Anupb7/anup-personal-llm",
		"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 "Anupb7/anup-personal-llm" \
        --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": "Anupb7/anup-personal-llm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Anupb7/anup-personal-llm with Docker Model Runner:
```
docker model run hf.co/Anupb7/anup-personal-llm
```

Personal Profile AI — QLoRA Adapter

A small QLoRA fine-tuned adapter built on top of Qwen/Qwen2.5-1.5B-Instruct.

This project demonstrates how an instruction-following LLM can be fine-tuned to answer questions about a structured personal/professional profile.

Important: The information used to train this model is synthetic data created for experimentation and demonstration purposes. It does not represent the real personal information, employment history, education, achievements, or other attributes of a real person.

Model Details

Model Description

This model is a LoRA adapter fine-tuned using supervised fine-tuning (SFT) with QLoRA techniques.

The objective is to teach the base language model to respond to questions about a fictional/synthetic professional profile.

The model is intended primarily as an educational demonstration of:

LLM fine-tuning
QLoRA
LoRA adapters
Instruction tuning
Hugging Face Transformers
PEFT
TRL
Synthetic instruction datasets
Personal-profile AI assistants

Model Type

Base model: Qwen/Qwen2.5-1.5B-Instruct
Fine-tuning method: QLoRA / LoRA
Training objective: Supervised Fine-Tuning (SFT)
Architecture: Causal Language Model
Adapter framework: PEFT
Training framework: TRL
Precision: 4-bit quantized base model during training
Language: English

Developed By

Anup Batakurki

Model License

This adapter follows the licensing terms of the base model. Please also review the Qwen model license before redistribution or commercial use.

Base Model

This adapter was fine-tuned from:

Qwen/Qwen2.5-1.5B-Instruct

Intended Uses

Direct Use

The adapter can be used for experimentation with a synthetic professional-profile assistant.

Example applications include:

Resume AI assistants
Interview preparation assistants
Professional profile chatbots
LLM fine-tuning demonstrations
QLoRA learning projects
Instruction-tuning experiments
Educational demonstrations of PEFT

Downstream Use

The adapter can be integrated into applications that combine a language model with a structured profile or retrieval system.

For example:

User Question
      |
      v
Profile / Knowledge Retrieval
      |
      v
Qwen Base Model + LoRA Adapter
      |
      v
Generated Response

Downloads last month: 30

Model tree for Anupb7/anup-personal-llm

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Adapter

(1612)

this model