Instructions to use aryan27/geometry-function-finetuned-tinyllama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use aryan27/geometry-function-finetuned-tinyllama with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="aryan27/geometry-function-finetuned-tinyllama", filename="Merged_Model_Hf-1.1B-F16.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use aryan27/geometry-function-finetuned-tinyllama with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf aryan27/geometry-function-finetuned-tinyllama:F16 # Run inference directly in the terminal: llama-cli -hf aryan27/geometry-function-finetuned-tinyllama:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf aryan27/geometry-function-finetuned-tinyllama:F16 # Run inference directly in the terminal: llama-cli -hf aryan27/geometry-function-finetuned-tinyllama: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 aryan27/geometry-function-finetuned-tinyllama:F16 # Run inference directly in the terminal: ./llama-cli -hf aryan27/geometry-function-finetuned-tinyllama: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 aryan27/geometry-function-finetuned-tinyllama:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf aryan27/geometry-function-finetuned-tinyllama:F16
Use Docker
docker model run hf.co/aryan27/geometry-function-finetuned-tinyllama:F16
- LM Studio
- Jan
- Ollama
How to use aryan27/geometry-function-finetuned-tinyllama with Ollama:
ollama run hf.co/aryan27/geometry-function-finetuned-tinyllama:F16
- Unsloth Studio new
How to use aryan27/geometry-function-finetuned-tinyllama 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 aryan27/geometry-function-finetuned-tinyllama 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 aryan27/geometry-function-finetuned-tinyllama to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for aryan27/geometry-function-finetuned-tinyllama to start chatting
- Docker Model Runner
How to use aryan27/geometry-function-finetuned-tinyllama with Docker Model Runner:
docker model run hf.co/aryan27/geometry-function-finetuned-tinyllama:F16
- Lemonade
How to use aryan27/geometry-function-finetuned-tinyllama with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull aryan27/geometry-function-finetuned-tinyllama:F16
Run and chat with the model
lemonade run user.geometry-function-finetuned-tinyllama-F16
List all available models
lemonade list
MiniLLM Geometry Engine
MiniLLM Geometry Engine is a specialized, fine-tuned version of the TinyLlama 1.1B language model, optimized for generating geometry-related functions for a geometry engine. By fine-tuning TinyLlama 1.1B on a custom Geometry Chain-of-Thought (CoT) dataset, MiniLLM Geometry Engine excels at producing accurate and efficient mathematical functions tailored for geometric computations.
Key Features
- Base Model: TinyLlama 1.1B, a lightweight and efficient language model.
- Fine-Tuning: Trained on a Geometry CoT dataset, enabling step-by-step reasoning for geometry problems.
- Output: Generates precise geometry functions (e.g., calculating areas, volumes, distances, or intersections) in a format compatible with geometry engines.
- Applications: Ideal for educational tools, CAD software, game development, and computational geometry tasks.
- Efficiency: Optimized for low-resource environments, balancing performance and computational cost.
Capabilities
MiniLLM Geometry Engine can interpret geometry-related queries and output functional code or mathematical expressions. For example, given a prompt like "Generate a function to calculate the area of a triangle," it produces executable code or formulas with clear reasoning, leveraging its CoT fine-tuning to ensure logical accuracy.
Technical Details
- Dataset: Custom Geometry CoT dataset, including problems on 2D/3D shapes, trigonometry, and coordinate geometry, with step-by-step solutions.
- Architecture: Inherits TinyLlama's transformer-based structure, fine-tuned to prioritize geometric reasoning.
- Output Format: Produces functions in Python or pseudocode, compatible with geometry engine APIs.
- Performance: Enhanced accuracy on geometry tasks compared to the base TinyLlama model, with minimal latency.
MiniLLM Geometry Engine is a powerful, compact solution for developers and researchers needing reliable geometry function generation in resource-constrained environments.
- Downloads last month
- 10
16-bit
Model tree for aryan27/geometry-function-finetuned-tinyllama
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0