Instructions to use ApyHTML19/NuTag 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 ApyHTML19/NuTag 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 ApyHTML19/NuTag:F16 # Run inference directly in the terminal: llama cli -hf ApyHTML19/NuTag:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ApyHTML19/NuTag:F16 # Run inference directly in the terminal: llama cli -hf ApyHTML19/NuTag:F16
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 ApyHTML19/NuTag:F16 # Run inference directly in the terminal: ./llama-cli -hf ApyHTML19/NuTag:F16
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 ApyHTML19/NuTag:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ApyHTML19/NuTag:F16
Use Docker
docker model run hf.co/ApyHTML19/NuTag:F16
- LM Studio
- Jan
- Ollama
How to use ApyHTML19/NuTag with Ollama:
ollama run hf.co/ApyHTML19/NuTag:F16
- Unsloth Studio
How to use ApyHTML19/NuTag 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 ApyHTML19/NuTag 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 ApyHTML19/NuTag to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ApyHTML19/NuTag to start chatting
- Docker Model Runner
How to use ApyHTML19/NuTag with Docker Model Runner:
docker model run hf.co/ApyHTML19/NuTag:F16
- Lemonade
How to use ApyHTML19/NuTag with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ApyHTML19/NuTag:F16
Run and chat with the model
lemonade run user.NuTag-F16
List all available models
lemonade list
- Atomic Chat
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 🏷️ NuTag — Named Entity Recognition Model
|
| 2 |
+
|
| 3 |
+
> **NuTag** est un modèle de reconnaissance d'entités nommées (NER) basé sur **NuNER-BERT-v1.0**, développé par [NuMind](https://huggingface.co/numind), quantifié au format **GGUF** pour une exécution locale légère et efficace.
|
| 4 |
+
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
## 📋 Informations générales
|
| 8 |
+
|
| 9 |
+
| Attribut | Détail |
|
| 10 |
+
|---|---|
|
| 11 |
+
| **Nom** | NuTag |
|
| 12 |
+
| **Architecture** | BERT (Bidirectional Encoder Representations from Transformers) |
|
| 13 |
+
| **Tâche** | Token Classification / Named Entity Recognition (NER) |
|
| 14 |
+
| **Langue** | Anglais 🇬🇧 |
|
| 15 |
+
| **Format** | GGUF (llama.cpp compatible) |
|
| 16 |
+
| **Licence** | Voir dépôt original NuMind |
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
## 🎯 À quoi sert NuTag ?
|
| 21 |
+
|
| 22 |
+
NuTag analyse un texte brut et **identifie automatiquement les entités nommées** qu'il contient. Il ne génère pas de texte — il **étiquette** les éléments importants.
|
| 23 |
+
|
| 24 |
+
### Entités détectées
|
| 25 |
+
|
| 26 |
+
| Étiquette | Type | Exemple |
|
| 27 |
+
|---|---|---|
|
| 28 |
+
| `PER` | Personne | *Elon Musk*, *Marie Curie* |
|
| 29 |
+
| `ORG` | Organisation | *Tesla*, *ONU*, *Google* |
|
| 30 |
+
| `LOC` | Lieu géographique | *Paris*, *Maroc*, *Sahara* |
|
| 31 |
+
| `DATE` | Date / Période | *12 janvier 2024*, *en 2003* |
|
| 32 |
+
| `MONEY` | Montant financier | *6,5 millions de dollars* |
|
| 33 |
+
| `MISC` | Divers | *iPhone 15*, *COVID-19* |
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
## 💡 Exemple d'utilisation
|
| 38 |
+
|
| 39 |
+
**Texte en entrée :**
|
| 40 |
+
```
|
| 41 |
+
Elon Musk a fondé Tesla à Palo Alto en 2003 avec un investissement de 6,5M$.
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
**Sortie NuTag :**
|
| 45 |
+
```json
|
| 46 |
+
[
|
| 47 |
+
{ "entity": "PER", "word": "Elon Musk", "score": 0.998 },
|
| 48 |
+
{ "entity": "ORG", "word": "Tesla", "score": 0.995 },
|
| 49 |
+
{ "entity": "LOC", "word": "Palo Alto", "score": 0.991 },
|
| 50 |
+
{ "entity": "DATE", "word": "2003", "score": 0.987 },
|
| 51 |
+
{ "entity": "MONEY", "word": "6,5M$", "score": 0.976 }
|
| 52 |
+
]
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
---
|
| 56 |
+
|
| 57 |
+
## 🚀 Installation & Usage
|
| 58 |
+
|
| 59 |
+
### Option 1 — HuggingFace Transformers (Python)
|
| 60 |
+
|
| 61 |
+
```bash
|
| 62 |
+
pip install transformers torch
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
```python
|
| 66 |
+
from transformers import pipeline
|
| 67 |
+
|
| 68 |
+
ner = pipeline(
|
| 69 |
+
task="ner",
|
| 70 |
+
model="numind/NuNER-BERT-v1.0",
|
| 71 |
+
aggregation_strategy="simple"
|
| 72 |
+
)
|
| 73 |
+
|
| 74 |
+
texte = "Elon Musk a fondé Tesla à Palo Alto en 2003 avec 6,5M$ d'investissement."
|
| 75 |
+
resultats = ner(texte)
|
| 76 |
+
|
| 77 |
+
for entite in resultats:
|
| 78 |
+
print(f"[{entite['entity_group']}] {entite['word']} (score: {entite['score']:.3f})")
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
---
|
| 82 |
+
|
| 83 |
+
### Option 3 — LM Studio (interface graphique)
|
| 84 |
+
|
| 85 |
+
1. Ouvrir **LM Studio**
|
| 86 |
+
2. Rechercher `ApyHTML19/NuTag`
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
## 🛠️ Cas d'usage
|
| 90 |
+
|
| 91 |
+
| Domaine | Application |
|
| 92 |
+
|---|---|
|
| 93 |
+
| 📰 **Presse & Médias** | Extraction automatique de personnes, lieux, événements |
|
| 94 |
+
| ⚖️ **Juridique** | Identification de parties, dates, montants dans des contrats |
|
| 95 |
+
| 🏥 **Santé** | Extraction de médicaments, pathologies, patients |
|
| 96 |
+
| 🔐 **Cybersécurité** | Détection d'IPs, domaines, CVE dans des logs |
|
| 97 |
+
| 📦 **E-commerce** | Reconnaissance de produits, marques, prix |
|
| 98 |
+
| 🔍 **Moteur de recherche** | Indexation sémantique de contenus |
|
| 99 |
+
|
| 100 |
+
---
|
| 101 |
+
|
| 102 |
+
## ⚙️ Caractéristiques techniques
|
| 103 |
+
|
| 104 |
+
- **Architecture** : BERT encoder-only (non génératif)
|
| 105 |
+
- **Méthode d'entraînement** : Fine-tuning supervisé sur corpus NER multidomaine
|
| 106 |
+
- **Tokenisation** : WordPiece (vocabulaire BERT)
|
| 107 |
+
- **Format GGUF** : Quantisation statique par `mradermacher`
|
| 108 |
+
- **Compatible** : `llama.cpp`, `LM Studio`, `Ollama`, `Jan`
|
| 109 |
+
|
| 110 |
+
---
|
| 111 |
+
|
| 112 |
+
## ⚠️ Limitations
|
| 113 |
+
|
| 114 |
+
- Modèle entraîné principalement sur des textes **en anglais**
|
| 115 |
+
- Ne génère **pas** de texte — uniquement classification de tokens
|
| 116 |
+
- Les quantisations basses (Q2, Q3) peuvent réduire la précision sur des entités rares
|
| 117 |
+
- Les entités composées (ex: *New York City*) peuvent être fragmentées selon la tokenisation
|
| 118 |
+
|
| 119 |
+
---
|
| 120 |
+
|
| 121 |
+
## 🔗 Liens utiles
|
| 122 |
+
|
| 123 |
+
- 📦 [Modèle original — numind/NuNER-BERT-v1.0](https://huggingface.co/numind/NuNER-BERT-v1.0)
|
| 124 |
+
- 📦 [Version GGUF — mradermacher/NuNER-BERT-v1.0-GGUF](https://huggingface.co/mradermacher/NuNER-BERT-v1.0-GGUF)
|
| 125 |
+
- 📖 [Guide GGUF par TheBloke](https://huggingface.co/TheBloke)
|
| 126 |
+
- 🛠️ [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
| 127 |
+
- 🖥️ [LM Studio](https://lmstudio.ai)
|
| 128 |
+
|
| 129 |
+
---
|