Instructions to use fernandotonon/QtMeshEditor-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use fernandotonon/QtMeshEditor-models 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 fernandotonon/QtMeshEditor-models:Q8_0
# Run inference directly in the terminal:
llama cli -hf fernandotonon/QtMeshEditor-models:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fernandotonon/QtMeshEditor-models:Q8_0
# Run inference directly in the terminal:
llama cli -hf fernandotonon/QtMeshEditor-models:Q8_0

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 fernandotonon/QtMeshEditor-models:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf fernandotonon/QtMeshEditor-models:Q8_0

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 fernandotonon/QtMeshEditor-models:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fernandotonon/QtMeshEditor-models:Q8_0

Use Docker

docker model run hf.co/fernandotonon/QtMeshEditor-models:Q8_0

LM Studio
Jan
Ollama
How to use fernandotonon/QtMeshEditor-models with Ollama:
```
ollama run hf.co/fernandotonon/QtMeshEditor-models:Q8_0
```

Unsloth Studio

How to use fernandotonon/QtMeshEditor-models 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 fernandotonon/QtMeshEditor-models 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 fernandotonon/QtMeshEditor-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fernandotonon/QtMeshEditor-models to start chatting

Docker Model Runner
How to use fernandotonon/QtMeshEditor-models with Docker Model Runner:
```
docker model run hf.co/fernandotonon/QtMeshEditor-models:Q8_0
```

Lemonade

How to use fernandotonon/QtMeshEditor-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fernandotonon/QtMeshEditor-models:Q8_0

Run and chat with the model

lemonade run user.QtMeshEditor-models-Q8_0

List all available models

lemonade list

Atomic Chat

fernandotonon commited on Jul 2

Commit

c492bdd

verified ·

1 Parent(s): c6af557

Segmentation section: document only the sources actually used

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -66,9 +66,8 @@ leg labels per point (PointNet++-style, two kNN aggregation blocks). **Trained
 from scratch** (v2) by the QtMeshEditor project on **surface-sampled synthetic
 bodies we own** (humanoid incl. chibi, quadruped, biped-with-tail — exact
 by-construction labels, CC0) mixed with **CC0 rigged characters mined for
-exact rig-derived labels** (Quaternius packs). Sidesteps the non-commercial
-ShapeNet-Part / PartNet datasets. **94.7%** per-vertex accuracy on rig-truth
-eval (v1: 31.5%). **Dedicated repo (full model card + eval data):**
 [fernandotonon/QtMeshEditor-mesh-segmentation](https://huggingface.co/fernandotonon/QtMeshEditor-mesh-segmentation).
 Downloaded into `<AppData>/ai_models/segment/`. License: CC-BY-4.0.

 from scratch** (v2) by the QtMeshEditor project on **surface-sampled synthetic
 bodies we own** (humanoid incl. chibi, quadruped, biped-with-tail — exact
 by-construction labels, CC0) mixed with **CC0 rigged characters mined for
+exact rig-derived labels** (Quaternius packs). **94.7%** per-vertex accuracy
+on rig-truth eval (v1: 31.5%). **Dedicated repo (full model card + eval data):**
 [fernandotonon/QtMeshEditor-mesh-segmentation](https://huggingface.co/fernandotonon/QtMeshEditor-mesh-segmentation).
 Downloaded into `<AppData>/ai_models/segment/`. License: CC-BY-4.0.