Instructions to use rahul7star/Math-AI-Full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rahul7star/Math-AI-Full with Transformers:

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

pipe = pipeline("image-text-to-text", model="rahul7star/Math-AI-Full")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("rahul7star/Math-AI-Full")
model = AutoModelForImageTextToText.from_pretrained("rahul7star/Math-AI-Full")
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?"}
        ]
    },
]
inputs = processor.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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use rahul7star/Math-AI-Full with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rahul7star/Math-AI-Full",
	filename="rahul7star_Math-AI-Full-Q4_K_M.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 rahul7star/Math-AI-Full with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rahul7star/Math-AI-Full:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf rahul7star/Math-AI-Full:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rahul7star/Math-AI-Full:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf rahul7star/Math-AI-Full: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 rahul7star/Math-AI-Full:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rahul7star/Math-AI-Full: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 rahul7star/Math-AI-Full:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rahul7star/Math-AI-Full:Q4_K_M

Use Docker

docker model run hf.co/rahul7star/Math-AI-Full:Q4_K_M

LM Studio
Jan

vLLM

How to use rahul7star/Math-AI-Full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rahul7star/Math-AI-Full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rahul7star/Math-AI-Full",
		"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/rahul7star/Math-AI-Full:Q4_K_M

SGLang

How to use rahul7star/Math-AI-Full 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 "rahul7star/Math-AI-Full" \
    --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": "rahul7star/Math-AI-Full",
		"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 "rahul7star/Math-AI-Full" \
        --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": "rahul7star/Math-AI-Full",
		"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 rahul7star/Math-AI-Full with Ollama:
```
ollama run hf.co/rahul7star/Math-AI-Full:Q4_K_M
```

Unsloth Studio new

How to use rahul7star/Math-AI-Full 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 rahul7star/Math-AI-Full 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 rahul7star/Math-AI-Full to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rahul7star/Math-AI-Full to start chatting

Pi new

How to use rahul7star/Math-AI-Full with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rahul7star/Math-AI-Full: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": "rahul7star/Math-AI-Full:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rahul7star/Math-AI-Full with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rahul7star/Math-AI-Full: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 rahul7star/Math-AI-Full:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use rahul7star/Math-AI-Full with Docker Model Runner:
```
docker model run hf.co/rahul7star/Math-AI-Full:Q4_K_M
```

Lemonade

How to use rahul7star/Math-AI-Full with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rahul7star/Math-AI-Full:Q4_K_M

Run and chat with the model

lemonade run user.Math-AI-Full-Q4_K_M

List all available models

lemonade list

Demo

https://huggingface.co/spaces/rahul7star/Math-AI

Model usage

This model is designed specifically for Hindi-speaking learners who want to understand mathematics, science, and coding in a clear and accessible way. It focuses on explaining concepts in simple Hindi, making complex topics easier to grasp without requiring strong English proficiency. Whether you're solving math problems, learning scientific principles, or exploring programming concepts, the model provides responses primarily in Hindi to ensure a comfortable learning experience. Its goal is to bridge the language gap in technical education and empower users to learn, practice, and grow in their native language.

यह मॉडल विशेष रूप से हिंदी बोलने वाले शिक्षार्थियों के लिए बनाया गया है, ताकि वे गणित, विज्ञान और कोडिंग को आसानी से समझ सकें। यह जटिल विषयों को सरल और स्पष्ट हिंदी में समझाता है, जिससे बिना मजबूत अंग्रेज़ी ज्ञान के भी सीखना संभव हो जाता है। चाहे आप गणित के सवाल हल कर रहे हों, वैज्ञानिक सिद्धांत समझ रहे हों या प्रोग्रामिंग सीख रहे हों, यह मॉडल मुख्य रूप से हिंदी में उत्तर देता है ताकि सीखने का अनुभव सहज और प्रभावी बने। इसका उद्देश्य तकनीकी शिक्षा में भाषा की बाधा को दूर करना और उपयोगकर्ताओं को उनकी मातृभाषा में सीखने, अभ्यास करने और आगे बढ़ने के लिए सक्षम बनाना है।

a model to learn maths science coding in hindi language

A Hindi Math Model


Question ->
 Pythagoras Theorem?

Output -> 

Iska accurate explanation ye hai: Right-angled triangle mein a² + b² = c² hota hai.

set think to false if you dont want model to think

https://huggingface.co/spaces/rahul7star/Math-AI

Try this way

use this way if you wan model to ans st away

System:
You are a concise and clear assistant. Follow these rules strictly:
1. Do NOT include reasoning, chain-of-thought, or internal thinking.
2. Only provide a short explanation if necessary (max 1–2 lines).
3. After the short explanation, give the final answer only.
4. Do not add any extra text, comments, or verbose elaboration.

Always follow this format:

Explanation (optional, max 2 lines):
<short explanation here, or leave blank>

Answer:
<final answer here>

User:
Write a Python program to add two numbers.





response


<<<reasoning_content_start>>>
Mere mutabik, Do numbers ko add karne ke liye ek function use hota hai jo return karti hai. Iska explanation iska right way hai: Numbers ka sum calculate karte hain.

Yahan iska accurate explanation hai: Yahan do numbers ki addition ka code diya gaya hai.
<<<reasoning_content_end>>>Iska Explanation ye hai: Do numbers ko add karne ke liye ek simple function use hota hai jo return karti hai. Answer : def add(a, b): return a + b

USAGE TIPS -Ask in hindi

if you want to ask - "What is gravity?" ask in this way

System:
You are a concise and clear assistant. Follow these rules strictly:
1. Do NOT include reasoning, chain-of-thought, or internal thinking.
2. Only provide a short explanation if necessary (max 1–2 lines).
3. Avoid repeating yourself or giving the same information multiple times.
4. After the short explanation, give the final answer only.
5. Do not add any extra text, comments, or verbose elaboration.

Always follow this format:

Explanation (optional, max 2 lines):
<short explanation here, or leave blank>

Answer:
<final answer here>

User:
What is gravity? Explain in Hindi.

Model response

Answer



Iska accurate explanation ye hai: Gravity ek force hoti hai
jo objects ko mutabik attract karti hai. Mere mutabik,
Wo wo power hai jo earth aur other planets par matter ko pull karti hai.
Iska correct definition iska hai ki wo attraction force hai jo mass wale objects ko ek-dos se draw karne
 ka prabhav darti hai.

Downloads last month: 73

Safetensors

Model size

5B params

Tensor type

BF16

F32

Model tree for rahul7star/Math-AI-Full

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(185)

this model

Quantizations

1 model

rahul7star
/

Math-AI-Full