Instructions to use brodatech/finance-phi3-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use brodatech/finance-phi3-gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="brodatech/finance-phi3-gguf", filename="phi-3-mini-4k-instruct.Q4_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use brodatech/finance-phi3-gguf with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf brodatech/finance-phi3-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf brodatech/finance-phi3-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 brodatech/finance-phi3-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf brodatech/finance-phi3-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 brodatech/finance-phi3-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf brodatech/finance-phi3-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 brodatech/finance-phi3-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf brodatech/finance-phi3-gguf:Q4_K_M
Use Docker
docker model run hf.co/brodatech/finance-phi3-gguf:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use brodatech/finance-phi3-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "brodatech/finance-phi3-gguf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "brodatech/finance-phi3-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/brodatech/finance-phi3-gguf:Q4_K_M
- Ollama
How to use brodatech/finance-phi3-gguf with Ollama:
ollama run hf.co/brodatech/finance-phi3-gguf:Q4_K_M
- Unsloth Studio
How to use brodatech/finance-phi3-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 brodatech/finance-phi3-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 brodatech/finance-phi3-gguf to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for brodatech/finance-phi3-gguf to start chatting
- Docker Model Runner
How to use brodatech/finance-phi3-gguf with Docker Model Runner:
docker model run hf.co/brodatech/finance-phi3-gguf:Q4_K_M
- Lemonade
How to use brodatech/finance-phi3-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull brodatech/finance-phi3-gguf:Q4_K_M
Run and chat with the model
lemonade run user.finance-phi3-gguf-Q4_K_M
List all available models
lemonade list
| import os | |
| from llama_cpp import Llama | |
| MODEL_FILENAME = "phi-3-mini-4k-instruct.Q4_K_M.gguf" | |
| current_dir = os.path.dirname(os.path.abspath(__file__)) | |
| model_path = os.path.join(current_dir, MODEL_FILENAME) | |
| SYSTEM_PROMPT = """ | |
| You are a professional Financial Analyst with expertise in: | |
| - Stock market analysis and valuation | |
| - Corporate finance and accounting | |
| - Investment strategy and portfolio management | |
| - Economic trends and market indicators | |
| - Risk assessment and financial modeling | |
| Your responses should be: | |
| 1. Accurate and data-driven | |
| 2. Professional and neutral in tone | |
| 3. Comprehensive yet concise | |
| 4. Based on sound financial principles | |
| Always provide specific examples and metrics when relevant. | |
| """ | |
| # Check if model file exists | |
| if not os.path.exists(model_path): | |
| print(f"\n❌ Model file '{MODEL_FILENAME}' not found.") | |
| print("Make sure the GGUF file is in the same folder as main.py\n") | |
| exit() | |
| print("\n🧠 Loading Financial Analyst AI model...\n") | |
| try: | |
| llm = Llama( | |
| model_path=model_path, | |
| n_ctx=1024, | |
| n_threads=os.cpu_count(), | |
| chat_format="phi-3", | |
| verbose=False | |
| ) | |
| print("✅ Model loaded successfully!") | |
| except Exception as e: | |
| print(f"\n❌ Failed to load model:\n{e}") | |
| exit() | |
| print("\n" + "=" * 60) | |
| print("📈 Financial Analyst AI") | |
| print("Type 'exit' or 'quit' to stop.") | |
| print("=" * 60) | |
| while True: | |
| user_input = input("\nYou: ") | |
| if user_input.lower() in ["exit", "quit", "q"]: | |
| print("\nGoodbye!") | |
| break | |
| if not user_input.strip(): | |
| continue | |
| print("\nAnalyst: ", end="", flush=True) | |
| try: | |
| response = llm.create_chat_completion( | |
| messages=[ | |
| { | |
| "role": "system", | |
| "content": SYSTEM_PROMPT | |
| }, | |
| { | |
| "role": "user", | |
| "content": user_input | |
| } | |
| ], | |
| max_tokens=512, | |
| temperature=0.2, | |
| top_p=0.9, | |
| stop=[ | |
| "<|user|>", | |
| "<|assistant|>" | |
| ], | |
| stream=True | |
| ) | |
| for chunk in response: | |
| delta = chunk["choices"][0]["delta"] | |
| if "content" in delta: | |
| print(delta["content"], end="", flush=True) | |
| print() | |
| except KeyboardInterrupt: | |
| print("\n\nStopped by user.") | |
| break | |
| except Exception as e: | |
| print(f"\n❌ Error: {e}") |