Instructions to use xsanskarx/qwen2-0.5b_numina_math-instruct-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xsanskarx/qwen2-0.5b_numina_math-instruct-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xsanskarx/qwen2-0.5b_numina_math-instruct-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xsanskarx/qwen2-0.5b_numina_math-instruct-gguf 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 xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16
# Run inference directly in the terminal:
llama cli -hf xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16
# Run inference directly in the terminal:
llama cli -hf xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16

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 xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16

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 xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16

Use Docker

docker model run hf.co/xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16

LM Studio
Jan
Ollama
How to use xsanskarx/qwen2-0.5b_numina_math-instruct-gguf with Ollama:
```
ollama run hf.co/xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16
```
Unsloth Desktop
Docker Model Runner
How to use xsanskarx/qwen2-0.5b_numina_math-instruct-gguf with Docker Model Runner:
```
docker model run hf.co/xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16
```

Lemonade

How to use xsanskarx/qwen2-0.5b_numina_math-instruct-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xsanskarx/qwen2-0.5b_numina_math-instruct-gguf:F16

Run and chat with the model

lemonade run user.qwen2-0.5b_numina_math-instruct-gguf-F16

List all available models

lemonade list

Atomic Chat

xsanskarx/qwen2-0.5b_numina_math-instruct-gguf

This repository contains a gguf fine-tuned version of the Qwen-2 0.5B model specifically optimized for mathematical instruction understanding and reasoning. It builds upon the Numina dataset, which provides a rich source of mathematical problems and solutions designed to enhance reasoning capabilities even in smaller language models.

Motivation

My primary motivation is the hypothesis that high-quality datasets focused on mathematical reasoning can significantly improve the performance of smaller models on tasks that require logical deduction and problem-solving. Uploading comprehensive benchmarks is the next step in evaluating this claim.

Model Details

Base Model: Qwen-2 0.5B
Fine-tuning Dataset: Numina
Key Improvements: Enhanced ability to parse mathematical instructions, solve problems, and provide step-by-step explanations.

Downloads last month: 51

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

16-bit

Inference Providers NEW

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

xsanskarx
/

qwen2-0.5b_numina_math-instruct-gguf

xsanskarx/qwen2-0.5b_numina_math-instruct-gguf

Motivation

Model Details

Dataset used to train xsanskarx/qwen2-0.5b_numina_math-instruct-gguf