Instructions to use Anudeeprao1/stats-tutor-llama3.2-11b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Anudeeprao1/stats-tutor-llama3.2-11b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Anudeeprao1/stats-tutor-llama3.2-11b",
	filename="stats-tutor-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Anudeeprao1/stats-tutor-llama3.2-11b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

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/stats-tutor-llama3.2-11b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

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/stats-tutor-llama3.2-11b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

Use Docker

docker model run hf.co/Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

LM Studio
Jan
Ollama
How to use Anudeeprao1/stats-tutor-llama3.2-11b with Ollama:
```
ollama run hf.co/Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M
```

Unsloth Studio new

How to use Anudeeprao1/stats-tutor-llama3.2-11b 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/stats-tutor-llama3.2-11b 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/stats-tutor-llama3.2-11b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Anudeeprao1/stats-tutor-llama3.2-11b to start chatting

Pi new

How to use Anudeeprao1/stats-tutor-llama3.2-11b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

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/stats-tutor-llama3.2-11b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Anudeeprao1/stats-tutor-llama3.2-11b 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/stats-tutor-llama3.2-11b: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 Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Anudeeprao1/stats-tutor-llama3.2-11b with Docker Model Runner:
```
docker model run hf.co/Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M
```

Lemonade

How to use Anudeeprao1/stats-tutor-llama3.2-11b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Anudeeprao1/stats-tutor-llama3.2-11b:Q4_K_M

Run and chat with the model

lemonade run user.stats-tutor-llama3.2-11b-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Statistics Tutor — Llama 3.2 11B Vision

A fine-tuned vision-language model for teaching statistics and probability from elementary to advanced level. Trained on 9,243 multimodal QA pairs from 36 statistics textbooks.

Capabilities

Reads textbook pages, handwritten notes, charts, graphs, and formulas
Provides hint-based teaching (guides students, doesn't just give answers)
Refuses non-statistics questions (built-in guardrails)
Explains formulas variable-by-variable
Handles both text-only and image+text inputs

Training details

Base model: unsloth/Llama-3.2-11B-Vision-Instruct
Method: QLoRA (4-bit quantization)
Training framework: Unsloth + TRL SFTTrainer
Hardware: NVIDIA RTX 4500 Ada (24GB VRAM)
Epochs: 3
Effective batch size: 16
Learning rate: 2e-4 (cosine schedule)
LoRA rank: 16, alpha: 32

Dataset

9,243 question-answer pairs (6,470 train / 1,386 val / 1,387 test)
Generated using LLaVA 13B from 4,424 textbook page images
Sources: 36 statistics textbooks (Statistics Done Wrong, ISLR, etc.)

Usage

Python

from transformers import AutoModelForVision2Seq, AutoProcessor
from PIL import Image
import torch

model = AutoModelForVision2Seq.from_pretrained(
    "Anudeeprao1/stats-tutor-llama3.2-11b",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("Anudeeprao1/stats-tutor-llama3.2-11b")

# Ask a question
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": Image.open("textbook_page.png")},
        {"type": "text",  "text": "Explain this formula step by step"}
    ]
}]

text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=text, images=Image.open("textbook_page.png"), return_tensors="pt").to("cuda")
output = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(output[0], skip_special_tokens=True))

LM Studio (GUI — no coding)

Download LM Studio
Search: Anudeeprao1/stats-tutor-llama3.2-11b
Download and chat!

System prompt

The model expects this system prompt to be prepended to questions:

You are an expert statistics tutor specializing in teaching statistics and probability. Always give hints first to guide the student toward the answer. Only provide complete solution if explicitly asked. If asked anything NOT related to statistics or probability respond: "I am a statistics tutor and can only help with statistics and probability questions."

Author

Anudeep — fine-tuned for educational research purposes.

License

Apache 2.0

Downloads last month: 301

Safetensors

Model size

11B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Anudeeprao1
/

stats-tutor-llama3.2-11b