Instructions to use lucifrrrrrrrrrr/vn-geography-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use lucifrrrrrrrrrr/vn-geography-8b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="lucifrrrrrrrrrr/vn-geography-8b", filename="Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use lucifrrrrrrrrrr/vn-geography-8b with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf lucifrrrrrrrrrr/vn-geography-8b: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 lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf lucifrrrrrrrrrr/vn-geography-8b: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 lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
Use Docker
docker model run hf.co/lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use lucifrrrrrrrrrr/vn-geography-8b with Ollama:
ollama run hf.co/lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
- Unsloth Studio
How to use lucifrrrrrrrrrr/vn-geography-8b 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 lucifrrrrrrrrrr/vn-geography-8b 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 lucifrrrrrrrrrr/vn-geography-8b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for lucifrrrrrrrrrr/vn-geography-8b to start chatting
- Pi
How to use lucifrrrrrrrrrr/vn-geography-8b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use lucifrrrrrrrrrr/vn-geography-8b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use lucifrrrrrrrrrr/vn-geography-8b with Docker Model Runner:
docker model run hf.co/lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
- Lemonade
How to use lucifrrrrrrrrrr/vn-geography-8b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull lucifrrrrrrrrrr/vn-geography-8b:Q4_K_M
Run and chat with the model
lemonade run user.vn-geography-8b-Q4_K_M
List all available models
lemonade list
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Vietnam Geography Expert 8B (Llama-3.1 SFT)
This model is a specialized Large Language Model fine-tuned to be a domain expert in Vietnamese Geography. It has been trained on official curriculum data, covering physical geography, socio-economics, and regional analysis of Vietnam.
Model Description
The Vietnam Geography Expert 8B is specifically engineered to provide structured, logical, and factually accurate explanations. It is optimized to interpret complex geographical relationships and present them in a clear, pedagogical manner suitable for students, educators, and researchers.
Key Features
Structured Reasoning
The model is fine-tuned to organize responses into a logical Step 1, Step 2, Step 3 format, ensuring clarity and ease of understanding.Domain-Specific Accuracy
Trained on 900+ curated Q&A pairs derived from standard Vietnamese geography textbooks and national curriculum standards.Linguistic Precision
Optimized for professional Vietnamese, ensuring that geographical terminology (e.g., feralit soil, basalt, monsoon patterns) is used correctly within context.Instruction Adherence
Highly responsive to the Llama 3.1 Instruct format, reducing hallucinations and staying strictly within the provided system constraints.
Prompt Template
This model follows the Llama 3.1 Instruct template. To achieve the best results and ensure the structured Step-by-Step formatting, please use the following structure:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are an expert in Vietnamese Geography. Always provide answers using a structured Step 1, Step 2 approach.<|eot_id|>
<|start_header_id|>user<|end_header_id|>
{Your Question}<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
- Downloads last month
- 33