Instructions to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Anudeeprao1/Qwen3VL-2B-StatBot_Instruct") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Anudeeprao1/Qwen3VL-2B-StatBot_Instruct", dtype="auto") - llama-cpp-python
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Anudeeprao1/Qwen3VL-2B-StatBot_Instruct", filename="Qwen3VL-2B-StatBot-Q8_0.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0 # Run inference directly in the terminal: llama-cli -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0 # Run inference directly in the terminal: llama-cli -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Use Docker
docker model run hf.co/Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
- LM Studio
- Jan
- vLLM
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Anudeeprao1/Qwen3VL-2B-StatBot_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": "Anudeeprao1/Qwen3VL-2B-StatBot_Instruct", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
- SGLang
How to use Anudeeprao1/Qwen3VL-2B-StatBot_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 "Anudeeprao1/Qwen3VL-2B-StatBot_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": "Anudeeprao1/Qwen3VL-2B-StatBot_Instruct", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "Anudeeprao1/Qwen3VL-2B-StatBot_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": "Anudeeprao1/Qwen3VL-2B-StatBot_Instruct", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Ollama
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Ollama:
ollama run hf.co/Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
- Unsloth Studio new
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Anudeeprao1/Qwen3VL-2B-StatBot_Instruct to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Anudeeprao1/Qwen3VL-2B-StatBot_Instruct to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Anudeeprao1/Qwen3VL-2B-StatBot_Instruct to start chatting
- Pi new
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
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 Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Run Hermes
hermes
- Docker Model Runner
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Docker Model Runner:
docker model run hf.co/Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
- Lemonade
How to use Anudeeprao1/Qwen3VL-2B-StatBot_Instruct with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Anudeeprao1/Qwen3VL-2B-StatBot_Instruct:Q8_0
Run and chat with the model
lemonade run user.Qwen3VL-2B-StatBot_Instruct-Q8_0
List all available models
lemonade list
llm.create_chat_completion(
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
)- ๐ StatBot โ Qwen3-VL-2B Statistics Tutor for High School Students
- ๐ฏ What This Model Does
- ๐ Files in This Repo
- ๐ฑ How to Use on Your Phone (PocketPal)
- ๐ป How to Use with Ollama
- ๐ป How to Use with llama.cpp
- ๐ก Example Questions
- ๐ก๏ธ Safety Features
- โ๏ธ Training Details
- ๐ Performance
- ๐ Intended Audience
- ๐๏ธ Compliance & Safety
- ๐ Try a Sample Conversation
- โ ๏ธ Limitations
- ๐ License
- ๐ค Author
- ๐ท๏ธ Citation
- ๐ Acknowledgments
- ๐ฏ What This Model Does
๐ StatBot โ Qwen3-VL-2B Statistics Tutor for High School Students
A safe, guardrailed AI tutor specifically designed for teaching statistics and probability to high school students (ages 14โ18). Built for the Oklahoma Department of Education project. Runs offline on phones via PocketPal.
๐ฏ What This Model Does
StatBot is a fine-tuned vision-language model that:
- ๐ Teaches statistics โ mean, median, distributions, hypothesis testing, probability, regression, and more
- ๐ผ๏ธ Reads images โ graphs, charts, histograms, textbook pages, handwritten formulas
- ๐ก๏ธ Refuses unsafe content โ off-topic questions, jailbreaks, inappropriate requests
- ๐ Supports students in distress โ empathy + counselor referral
- ๐ Uses hint-first teaching โ guides students rather than just giving answers
๐ Files in This Repo
| File | Size | What It Is |
|---|---|---|
Qwen3VL-2B-StatBot-Q8_0.gguf |
1.71 GB | Main model (Q8_0 quantized) |
Qwen3VL-2B-StatBot-mmproj.gguf |
782 MB | Vision projector (needed for images) |
โ ๏ธ Both files required for full image + text capability!
๐ฑ How to Use on Your Phone (PocketPal)
- Install PocketPal from your app store
- Open PocketPal โ Models โ Search HuggingFace
- Search:
Anudeeprao1/Qwen3VL-2B-StatBot_Instruct - Download BOTH files:
- โ
Qwen3VL-2B-StatBot-Q8_0.gguf - โ
Qwen3VL-2B-StatBot-mmproj.gguf
- โ
- Tap Load Model
- Start asking statistics questions or upload a graph!
๐ป How to Use with Ollama
ollama run hf.co/Anudeeprao1/Qwen3VL-2B-StatBot_Instruct
๐ป How to Use with llama.cpp
llama-server -hf Anudeeprao1/Qwen3VL-2B-StatBot_Instruct
Then open http://localhost:8080 in browser.
๐ก Example Questions
Text Only
- "What is the difference between mean and median?"
- "Explain the central limit theorem to me"
- "How do I calculate standard deviation step by step?"
- "What is a p-value?"
With Images
- Upload a histogram โ "What type of distribution is this?"
- Upload a textbook page โ "Explain this formula"
- Upload a scatter plot โ "What relationship does this show?"
- Upload a bar chart โ "Describe this data"
๐ก๏ธ Safety Features
StatBot is designed with 7 categories of guardrails:
| Category | Behavior |
|---|---|
| Off-topic questions | Refuses politely, redirects to stats |
| Inappropriate content | Refuses firmly |
| Identity probing | Deflects, never reveals internals |
| Jailbreak attempts | Resists prompt injection |
| Student distress | Shows empathy, refers to counselor |
| Privacy questions | Confirms FERPA + COPPA design |
| Educational audits | Provides compliance info |
โ๏ธ Training Details
| Parameter | Value |
|---|---|
| Base model | unsloth/Qwen3-VL-2B-Instruct |
| Fine-tuning method | LoRA SFT (Unsloth) |
| LoRA rank | 16 |
| Quantization | Q8_0 GGUF |
| Training samples | 7,202 |
| Guardrail samples | 720 (7 categories ร 3 repetitions) |
| Epochs | 3 |
| Learning rate | 2e-4 (cosine schedule) |
| Effective batch size | 16 |
| Max sequence length | 2048 |
| Hardware | NVIDIA RTX 4500 Ada (24 GB) |
| Framework | Unsloth + TRL + Transformers |
๐ Performance
- Final training loss: ~0.09
- Final validation loss: ~0.09
- Perplexity: ~1.1
- No overfitting detected (train โ val loss)
- Vision capability: Full multimodal support via mmproj
๐ Intended Audience
- โ High school statistics students (ages 14โ18)
- โ Oklahoma high school teachers (classroom aid)
- โ Statistics tutors needing safe AI assistance
- โ Educational researchers studying AI guardrails
- โ NOT for general-purpose chat (refuses non-stats)
- โ NOT for elementary/middle school content
๐๏ธ Compliance & Safety
- FERPA compliant design (no student data storage)
- COPPA compliant for under-13 protections
- Oklahoma DoE project deliverable
- No cross-session memory (every chat is private)
- Crisis-aware (refers to 988 Lifeline + adults)
๐ Try a Sample Conversation
User: "What is standard deviation?"
StatBot: "Great question! ๐ฏ Standard deviation tells us how spread out data is from the average...
Think of test scores: if everyone scored close to the average, SD is small. If scores are all over the place, SD is large.
Formula: ฯ = โ(ฮฃ(x - ฮผ)ยฒ / N)
Want me to walk through an example?"
User: "What is the capital of France?"
StatBot: "I'm StatBot, your statistics tutor designed for educational purposes only! I can only help with high school statistics topics. Try asking me about mean, median, probability, or graphs! Have a good day. ๐"
โ ๏ธ Limitations
- Only English language
- Only statistics/probability topics
- Best for high school level (ages 14โ18)
- Requires both GGUF files for image input
- Q8_0 quantization (high quality but ~2 GB)
๐ License
Apache 2.0 โ Free for educational and research use.
๐ค Author
Anudeep โ Oklahoma Department of Education AI Tutoring Project
For questions or collaboration: open a discussion on this repo!
๐ท๏ธ Citation
If you use this model in research, please cite:
@misc{statbot2026,
author = {Anudeep},
title = {StatBot: A Guardrailed Vision-Language Tutor for High School Statistics},
year = {2026},
publisher = {HuggingFace},
url = {https://huggingface.co/Anudeeprao1/Qwen3VL-2B-StatBot_Instruct}
}
๐ Acknowledgments
- Unsloth โ for the 2x faster fine-tuning framework
- Qwen team โ for the excellent base VL model
- Oklahoma DoE โ for funding this educational AI research
- PocketPal โ for offline mobile inference support
- Downloads last month
- 93
8-bit
Model tree for Anudeeprao1/Qwen3VL-2B-StatBot_Instruct
Base model
Qwen/Qwen3-VL-2B-Instruct
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Anudeeprao1/Qwen3VL-2B-StatBot_Instruct", filename="", )