Instructions to use Stephen16/SaphraFgt-1.0-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Stephen16/SaphraFgt-1.0-8B-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 Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Stephen16/SaphraFgt-1.0-8B-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 Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Stephen16/SaphraFgt-1.0-8B-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 Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Stephen16/SaphraFgt-1.0-8B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Stephen16/SaphraFgt-1.0-8B-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Stephen16/SaphraFgt-1.0-8B-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
- Ollama
How to use Stephen16/SaphraFgt-1.0-8B-GGUF with Ollama:
ollama run hf.co/Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Stephen16/SaphraFgt-1.0-8B-GGUF with Docker Model Runner:
docker model run hf.co/Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
- Lemonade
How to use Stephen16/SaphraFgt-1.0-8B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.SaphraFgt-1.0-8B-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M# Run inference directly in the terminal:
llama cli -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_MUse 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 Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_MBuild 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 Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_MUse Docker
docker model run hf.co/Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_MSaphraFgt 1.0 8B
A fine-tuned Meta Llama 3.1 8B coding model optimized for frontend development, HTML, CSS, JavaScript, UI/UX, bug fixing, code editing, and complete website generation.
β¨ Features
- β Complete HTML generation
- β CSS styling
- β JavaScript development
- β Responsive website creation
- β UI/UX implementation
- β Bug fixing
- β Code debugging
- β Code completion
- β Code refactoring
- β Frontend optimization
π Benchmarks
| Benchmark | Score |
|---|---|
| HumanEval (Pass@1) | 36.6% |
| MBPP (Pass@1) | 41.5% |
Benchmark Comparison
π― Optimized For
- HTML5
- CSS3
- JavaScript (ES6+)
- Responsive Web Design
- Landing Pages
- Dashboards
- Portfolio Websites
- E-commerce Websites
- UI Components
- Frontend Debugging
π» Ollama
Run locally using Ollama.
ollama run SaphraFgt/saphrafgt-1-0-8b
π¦ llama.cpp
llama-cli -m SaphraFgt-1.0-8B-Q4_K_M.gguf
π¬ Example Prompt
User
Create a responsive ecommerce homepage using HTML, CSS and JavaScript.
Assistant
Produces a complete responsive webpage with:
- Navigation Bar
- Hero Section
- Product Cards
- Responsive Layout
- Modern UI
- Clean CSS
- Interactive JavaScript
π Comparison
Compared against several open-source 7B coding models.
| Model | HumanEval | MBPP |
|---|---|---|
| SaphraFgt 1.0 8B | 36.6% | 41.5% |
| Code Llama 7B | 33.5% | 41.4% |
| Gemma 7B | 32.3% | 38.0% |
| Mistral 7B | 26.2% | 50.2% |
| LLaMA 2 7B | 16.8% | 20.8% |
βοΈ Quantization
Included GGUF format
- Q4_K_M
Optimized for llama.cpp and Ollama.
π¦ Files
| File | Description |
|---|---|
| SaphraFgt-1.0-8B-Q4_K_M.gguf | Recommended GGUF model |
| Modelfile | Ollama Modelfile |
π¨βπ» Creator
Seelam Reuben Stephen
π License
This model is based on Meta Llama 3.1 and follows the Llama 3.1 Community License.
β Support
If you find this model useful, please consider:
- β Liking the model
- π΄ Sharing it
- π Reporting issues
- π‘ Suggesting improvements
Happy Coding! π
- Downloads last month
- 197
4-bit
Model tree for Stephen16/SaphraFgt-1.0-8B-GGUF
Base model
meta-llama/Llama-3.1-8B
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M# Run inference directly in the terminal: llama cli -hf Stephen16/SaphraFgt-1.0-8B-GGUF:Q4_K_M