Instructions to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="kpakkiragari/PaperPilot-Qwen-0.5B-Instruct")
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("kpakkiragari/PaperPilot-Qwen-0.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("kpakkiragari/PaperPilot-Qwen-0.5B-Instruct", 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

llama.cpp

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

SGLang

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct 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 "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct" \
    --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": "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct",
		"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 "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct" \
        --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": "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with Ollama:
```
ollama run hf.co/kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M
```
Unsloth Desktop

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with Docker Model Runner:
```
docker model run hf.co/kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M
```

Lemonade

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.PaperPilot-Qwen-0.5B-Instruct-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kpakkiragari/PaperPilot-Qwen-0.5B-Instruct with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "kpakkiragari/PaperPilot-Qwen-0.5B-Instruct:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

PaperPilot-Qwen-0.5B-Instruct 📄✈️

PaperPilot-Qwen-0.5B-Instruct is an on-device, lightweight specialized small language model (SLM) fine-tuned on top of Qwen/Qwen2.5-0.5B-Instruct.

It is engineered specifically for private, air-gapped document intelligence and tool-calling, translating natural language user requests into single operations or multi-step chained pipelines across 78+ PaperPilot PDF and document tools.

Key Capabilities

Exact Schema Tool-Calling: Emits valid JSON tool calls for single and multi-step PDF workflows.
Dynamic Parameter Chaining: Automatically chains intermediate file paths (/tmp/inter_1.pdf -> /tmp/inter_2.pdf -> output.pdf) for complex multi-tool goals.
Ultra-Lightweight & Fast: Sub-50ms token generation; can run on-device via WebGPU/WASM, Tauri desktop, or llama.cpp.
Strict Privacy: 100% offline, zero cloud telemetry.

Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "KrushnaVardhanReddy/PaperPilot-Qwen-0.5B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {
        "role": "system",
        "content": "You are PaperPilot's on-device neural assistant. Convert user instructions into strict JSON tool calls. For single operations, emit a single JSON object. For multi-step workflows, emit a JSON array of tool calls chained in execution order."
    },
    {
        "role": "user",
        "content": "Combine document1.pdf and document2.pdf into merged.pdf and then compress it."
    }
]

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, do_sample=False)
print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True))

License

Apache-2.0 (Open Source)

Downloads last month: 605

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for kpakkiragari/PaperPilot-Qwen-0.5B-Instruct

Quantizations

1 model