Instructions to use kaushik-harsh-99/Math-Instruct-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="kaushik-harsh-99/Math-Instruct-v1-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kaushik-harsh-99/Math-Instruct-v1-GGUF", dtype="auto")

llama-cpp-python

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kaushik-harsh-99/Math-Instruct-v1-GGUF",
	filename="Math-Instruct-v1-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kaushik-harsh-99/Math-Instruct-v1-GGUF: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 kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kaushik-harsh-99/Math-Instruct-v1-GGUF: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 kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaushik-harsh-99/Math-Instruct-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaushik-harsh-99/Math-Instruct-v1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M

SGLang

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF 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 "kaushik-harsh-99/Math-Instruct-v1-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaushik-harsh-99/Math-Instruct-v1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "kaushik-harsh-99/Math-Instruct-v1-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaushik-harsh-99/Math-Instruct-v1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with Ollama:
```
ollama run hf.co/kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M
```

Unsloth Studio

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF 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 kaushik-harsh-99/Math-Instruct-v1-GGUF 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 kaushik-harsh-99/Math-Instruct-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kaushik-harsh-99/Math-Instruct-v1-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M
```

Lemonade

How to use kaushik-harsh-99/Math-Instruct-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kaushik-harsh-99/Math-Instruct-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Math-Instruct-v1-GGUF-Q4_K_M

List all available models

lemonade list

MathInstruct v1

MathInstruct v1 is a mathematics-focused instruction-tuned language model created by supervised fine-tuning a pretrained base model on curated mathematics training data.

This release aims to improve mathematical instruction following, solution generation, and benchmark performance while maintaining the original capabilities of the base model.

Results

Benchmark performance compared with the original base model is shown below.

$Benchmark Results$

MathInstruct v1 demonstrates improvements across mathematical evaluation tasks and stronger instruction-following behavior.

Training

MathInstruct v1 was trained using supervised fine-tuning (SFT) on the NVIDIA OpenMath dataset.

The model was trained for 0.1 epoch to adapt the base model toward stronger mathematical instruction following and solution generation while preserving its original capabilities.

Training setup: