Instructions to use hexera-org/GmshNet-8B-v0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use hexera-org/GmshNet-8B-v0.1-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="hexera-org/GmshNet-8B-v0.1-GGUF", filename="GmshNet-8B-v0.1-IQ2_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use hexera-org/GmshNet-8B-v0.1-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 hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf hexera-org/GmshNet-8B-v0.1-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 hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf hexera-org/GmshNet-8B-v0.1-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 hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf hexera-org/GmshNet-8B-v0.1-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 hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
Use Docker
docker model run hf.co/hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use hexera-org/GmshNet-8B-v0.1-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hexera-org/GmshNet-8B-v0.1-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": "hexera-org/GmshNet-8B-v0.1-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
- Ollama
How to use hexera-org/GmshNet-8B-v0.1-GGUF with Ollama:
ollama run hf.co/hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
- Unsloth Studio
How to use hexera-org/GmshNet-8B-v0.1-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 hexera-org/GmshNet-8B-v0.1-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 hexera-org/GmshNet-8B-v0.1-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for hexera-org/GmshNet-8B-v0.1-GGUF to start chatting
- Pi
How to use hexera-org/GmshNet-8B-v0.1-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hexera-org/GmshNet-8B-v0.1-GGUF: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": "hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use hexera-org/GmshNet-8B-v0.1-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hexera-org/GmshNet-8B-v0.1-GGUF: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 hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use hexera-org/GmshNet-8B-v0.1-GGUF with Docker Model Runner:
docker model run hf.co/hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
- Lemonade
How to use hexera-org/GmshNet-8B-v0.1-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hexera-org/GmshNet-8B-v0.1-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.GmshNet-8B-v0.1-GGUF-Q4_K_M
List all available models
lemonade list
GmshNet-8B-v0.1
GmshNet-8B-v0.1 is an open-source, dense, decoder-only 8B parameter large language model specializing in Gmsh 4.x meshing scripts, designed to produce structured analyses and generate robust geometry meshes through chain-of-thought reasoning.
Quickstart
Install Dependencies
pip install llama-cpp-python
Run Inference
from llama_cpp import Llama
# Input your prompt here
USER_INPUT = """
Create a 2D finite element mesh for a rectangular steel plate measuring 100 mm by 60 mm with a circular hole of radius 10 mm at its center (a classic stress-concentration test case). Refine the mesh around the hole to capture the stress gradient and use a coarser mesh near the outer edges. Define physical groups for the outer boundary and the hole so the mesh can be used for a finite element stress analysis.
"""
def load_model(model_path):
llm = Llama(
model_path=model_path,
n_ctx=32768,
n_gpu_layers=-1,
verbose=False
)
return llm
def generate_response(llm, user_input):
formatted_input = f"<gmsh_instruction>{user_input.strip()}</gmsh_instruction>"
messages = [{"role": "user", "content": formatted_input}]
response = llm.create_chat_completion(
messages=messages,
max_tokens=2000,
temperature=0.2,
top_k=20,
top_p=0.8,
repeat_penalty=1.1,
stream=False
)
return response['choices'][0]['message']['content']
def run_inference():
model_path = "" # Path to your model weights
llm = load_model(model_path)
result = generate_response(llm, USER_INPUT)
print(result)
if __name__ == "__main__":
run_inference()
Example Output
<think>
I need to analyze this meshing task step by step to create an effective GMSH script.
1. Geometry Requirements:
- Main domain: 100mm × 60mm rectangular plate
- Internal feature: Circular hole of radius 10mm at center
- Need refinement around hole for stress gradient capture
- Coarser mesh near outer edges
2. Meshing Approach:
- Unstructured triangular mesh for flexibility
- Size field to control refinement (finer near hole, coarser near edges)
- Physical groups for boundaries and hole surface
- Potential quadrilateral recombination in structured regions if needed
3. Construction Steps:
a) Create rectangle points and lines
b) Create circle points and arcs
c) Define line loops for plate and hole
d) Create plane surface with hole
e) Set mesh size fields for refinement
f) Define physical groups
g) Generate 2D mesh
</think>
<response>
1. High-level Overview:
- We'll create a rectangular plate with a circular hole at center
- Use size field to refine mesh near hole (radius 5mm from center)
- Coarser mesh grows outward from outer edges
- Physical groups for boundaries and hole surface
2. Step-by-step Instructions:
a) Create rectangle points (4 corners)
b) Connect with lines to form boundary
c) Create circle points (center + 4 quadrants)
d) Connect circle points with arcs
e) Define line loops for plate and hole
f) Create surface with hole
g) Set mesh size field with Attractor near hole
h) Define physical groups
i) Generate mesh
3. Complete GMSH Script:
```
// Rectangular Plate with Hole - Stress Concentration Test Case
// Geometry Parameters
plate_length = 100;
plate_width = 60;
hole_radius = 10;
// Mesh Sizing Parameters
base_size = 5; // Base mesh size
hole_refine = 1.0; // Size at hole center
hole_growth = 2.0; // Growth rate from hole to outer edges
// Create Rectangle Points
Point(1) = {0, 0, 0, base_size};
Point(2) = {plate_length, 0, 0, base_size};
Point(3) = {plate_length, plate_width, 0, base_size};
Point(4) = {0, plate_width, 0, base_size};
// Create Rectangle Edges
Line(1) = {1, 2};
Line(2) = {2, 3};
Line(3) = {3, 4};
Line(4) = {4, 1};
// Create Hole Points (center + 4 quadrants)
Point(5) = {plate_length/2, plate_width/2, 0, hole_refine}; // Center
Point(6) = {plate_length/2 + hole_radius, plate_width/2, 0, hole_refine};
Point(7) = {plate_length/2, plate_width/2 + hole_radius, 0, hole_refine};
Point(8) = {plate_length/2 - hole_radius, plate_width/2, 0, hole_refine};
Point(9) = {plate_length/2, plate_width/2 - hole_radius, 0, hole_refine};
// Create Hole Arcs
Circle(5) = {6, 5, 7};
Circle(6) = {7, 5, 8};
Circle(7) = {8, 5, 9};
Circle(8) = {9, 5, 6};
// Define Line Loops
Line Loop(1) = {1, 2, 3, 4}; // Outer boundary
Line Loop(2) = {5, 6, 7, 8}; // Hole boundary
// Create Surface with Hole
Plane Surface(1) = {1, 2};
// Mesh Size Field - Refinement near hole
Field[1] = Distance;
Field[1].NodesList = {5}; // Center point of hole
Field[2] = Threshold;
Field[2].IField = 1;
Field[2].LcMin = hole_refine;
Field[2].LcMax = base_size;
Field[2].DistMin = hole_radius;
Field[2].DistMax = plate_length/4;
Background Field = 2;
// Physical Groups
Physical Curve("OuterBoundary", 1) = {1, 2, 3, 4};
Physical Curve("HoleBoundary", 2) = {5, 6, 7, 8};
Physical Surface("Plate", 1) = {1};
// Mesh Settings
Mesh.Algorithm = 6; // Frontal-Delaunay
Mesh.Smoothing = 5; // More smoothing iterations
// Generate 2D Mesh
Mesh 2;
```
4. Implementation Notes:
- To run: Open in GMSH → Mesh → 2D
- Adjust parameters at top for different sizes/resolutions
- Visualize geometry (Geometry tab) before meshing to verify
- For quadrilateral mesh near hole, add:
```
Mesh.RecombineAll = 1;
Mesh.Algorithm = 8; // Delaunay for quads
```
- Common errors to avoid:
- Ensure line loops are properly closed
- Verify point IDs in circle definitions
- Check that surface includes both line loops (plate and hole)
</response>
- Downloads last month
- 329
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit