Spaces:
Runtime error
Runtime error
Commit ·
a61a8ff
1
Parent(s): bc84fc0
Professionalize API: Clean code, HF Model Hub integration, new README
Browse files- Dockerfile +4 -5
- README.md +37 -53
- main.py +77 -67
- mon_modele_darija_final/config.json +0 -54
- mon_modele_darija_final/model.safetensors +0 -3
- mon_modele_darija_final/special_tokens_map.json +0 -7
- mon_modele_darija_final/tokenizer.json +0 -0
- mon_modele_darija_final/tokenizer_config.json +0 -58
- mon_modele_darija_final/training_args.bin +0 -3
- mon_modele_darija_final/vocab.txt +0 -0
- requirements.txt +7 -14
Dockerfile
CHANGED
|
@@ -16,9 +16,8 @@ RUN pip install --no-cache-dir -r requirements.txt
|
|
| 16 |
# Cela inclut main.py et le dossier de votre modèle (ex: "marbert-darija-nlu-aicc")
|
| 17 |
COPY . .
|
| 18 |
|
| 19 |
-
#
|
| 20 |
-
EXPOSE
|
| 21 |
|
| 22 |
-
#
|
| 23 |
-
|
| 24 |
-
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
|
|
|
|
| 16 |
# Cela inclut main.py et le dossier de votre modèle (ex: "marbert-darija-nlu-aicc")
|
| 17 |
COPY . .
|
| 18 |
|
| 19 |
+
# Step 6: Expose the port used by the API (Hugging Face Spaces defaults to 7860)
|
| 20 |
+
EXPOSE 7860
|
| 21 |
|
| 22 |
+
# Step 7: Launch the API
|
| 23 |
+
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|
|
|
README.md
CHANGED
|
@@ -4,77 +4,61 @@ emoji: 🚀
|
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: blue
|
| 6 |
sdk: docker
|
| 7 |
-
app_port:
|
| 8 |
---
|
| 9 |
|
| 10 |
-
#
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
-
|
| 15 |
|
| 16 |
-
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
**➡️ [Tester l'API interactivement ici](https://mediani-darija-aicc-api.hf.space/docs)**
|
| 25 |
-
|
| 26 |
-
---
|
| 27 |
|
| 28 |
-
##
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
curl -X 'POST' \
|
| 38 |
-
'https://mediani-darija-aicc-api.hf.space/predict' \
|
| 39 |
-
-H 'accept: application/json' \
|
| 40 |
-
-H 'Content-Type: application/json' \
|
| 41 |
-
-d '{"text": "Salam, la connexion 4G naqsa 3ndi bzaf"}'
|
| 42 |
```
|
| 43 |
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
L'API retournera un objet JSON avec l'intention (intent) prédite par le modèle et son score de confiance (confidence).
|
| 47 |
-
|
| 48 |
```json
|
| 49 |
{
|
| 50 |
-
"intent": "
|
| 51 |
-
"confidence": 0.
|
| 52 |
}
|
| 53 |
```
|
| 54 |
|
| 55 |
-
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
-
|
| 62 |
-
- **reclamer_facture**: Réclamations concernant une facture (montant élevé, erreur...).
|
| 63 |
-
- **declarer_panne**: Signalement d'un problème technique (panne réseau, connexion lente...).
|
| 64 |
-
- **info_forfait**: Demandes d'informations sur les produits, offres et abonnements.
|
| 65 |
-
- **recuperer_mot_de_passe**: Demandes liées à la réinitialisation d'un mot de passe ou d'un code.
|
| 66 |
-
- **salutations**: Salutations et début de conversation.
|
| 67 |
-
- **remerciements**: Expressions de gratitude.
|
| 68 |
-
- **demander_agent_humain**: Demande explicite de parler à un conseiller humain.
|
| 69 |
-
- **hors_scope**: Toute demande hors du périmètre du service client.
|
| 70 |
|
| 71 |
-
|
|
|
|
|
|
|
|
|
|
| 72 |
|
| 73 |
-
|
| 74 |
|
| 75 |
-
|
| 76 |
-
- **Corpus**: Un corpus personnalisé a été assemblé en combinant la collecte de données (Twitter, YouTube), la génération par IA, et l'annotation manuelle avec Doccano.
|
| 77 |
-
- **Framework API**: FastAPI, pour sa rapidité et sa génération automatique de documentation.
|
| 78 |
-
- **Conteneurisation**: Docker, pour garantir la portabilité et la reproductibilité de l'environnement.
|
| 79 |
-
- **Versionnement**: Git & Git LFS pour gérer les gros fichiers de modèle (plus de 100 Mo).
|
| 80 |
-
- **Déploiement**: L'API est hébergée sur Hugging Face Spaces, fournissant une solution CI/CD (intégration et déploiement continus) à partir d'un dépôt Git.
|
|
|
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: blue
|
| 6 |
sdk: docker
|
| 7 |
+
app_port: 7860
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# Darija NLU API 🚀
|
| 11 |
|
| 12 |
+
[](https://mohammedmediani-darija-aicc-api.hf.space/docs)
|
| 13 |
+
[](https://python.org)
|
| 14 |
+
[](https://fastapi.tiangolo.com)
|
| 15 |
+
[](https://huggingface.co/mediani/marbert-fine-tuned-darija-aicc)
|
| 16 |
|
| 17 |
+
A professional REST API for **Natural Language Understanding (NLU)** in Moroccan Arabic (Darija). Designed to power intelligent contact centers and automated support systems.
|
| 18 |
|
| 19 |
+
## 🔗 Ecosystem
|
| 20 |
|
| 21 |
+
| Project | Description | Link |
|
| 22 |
+
|---------|-------------|------|
|
| 23 |
+
| 📺 **Demo App** | Interactive Streamlit UI | [Go to Space](https://huggingface.co/spaces/mediani/darija-nlu-demo) |
|
| 24 |
+
| 🧠 **Model** | Fine-tuned MARBERTv2 | [Go to Model](https://huggingface.co/mediani/marbert-fine-tuned-darija-aicc) |
|
| 25 |
+
| 💻 **Source Code** | GitHub Repository | [Go to GitHub](https://github.com/mohammedmediani/aicc-nlu-api) |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
+
## 🚀 Quick Usage
|
| 28 |
|
| 29 |
+
### Endpoint: `/predict` (POST)
|
| 30 |
|
| 31 |
+
**Request:**
|
| 32 |
+
```json
|
| 33 |
+
{
|
| 34 |
+
"text": "bghit n3raf solde dyali"
|
| 35 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
```
|
| 37 |
|
| 38 |
+
**Response:**
|
|
|
|
|
|
|
|
|
|
| 39 |
```json
|
| 40 |
{
|
| 41 |
+
"intent": "consulter_solde",
|
| 42 |
+
"confidence": 0.985
|
| 43 |
}
|
| 44 |
```
|
| 45 |
|
| 46 |
+
### Try it with cURL
|
| 47 |
|
| 48 |
+
```bash
|
| 49 |
+
curl -X 'POST' \
|
| 50 |
+
'https://mohammedmediani-darija-aicc-api.hf.space/predict' \
|
| 51 |
+
-H 'Content-Type: application/json' \
|
| 52 |
+
-d '{"text": "llah ykhalik bghit nchof factura"}'
|
| 53 |
+
```
|
| 54 |
|
| 55 |
+
## 📋 Features
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
+
- **9 Intent Categories**: From balance checks (`consulter_solde`) to technical support (`declarer_panne`).
|
| 58 |
+
- **High Performance**: Fine-tuned MARBERTv2 achieving >92% F1-score.
|
| 59 |
+
- **Production Ready**: Built with FastAPI, utilizing async capabilities and robust error handling.
|
| 60 |
+
- **Code-Switching**: Handles mixed Darija/French input natively.
|
| 61 |
|
| 62 |
+
## 📄 License
|
| 63 |
|
| 64 |
+
Apache 2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
main.py
CHANGED
|
@@ -1,98 +1,108 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
import
|
| 4 |
-
from
|
| 5 |
-
from pydantic import BaseModel
|
| 6 |
-
from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
|
| 7 |
from typing import Dict, Any
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
# --- Configuration ---
|
| 10 |
-
|
| 11 |
-
MODEL_PATH = "./mon_modele_darija_final"
|
| 12 |
|
| 13 |
-
#
|
| 14 |
-
|
| 15 |
-
# C'est une bonne pratique pour éviter de recharger le modèle à chaque requête.
|
| 16 |
-
try:
|
| 17 |
-
print("Chargement du tokenizer et du modèle MARBERT fine-tuné...")
|
| 18 |
-
|
| 19 |
-
# On spécifie le device (GPU si disponible, sinon CPU)
|
| 20 |
-
device = 0 if torch.cuda.is_available() else -1
|
| 21 |
-
|
| 22 |
-
# Création du pipeline de classification de texte de Hugging Face.
|
| 23 |
-
# C'est la manière la plus simple d'utiliser un modèle pour l'inférence.
|
| 24 |
-
nlu_pipeline = pipeline(
|
| 25 |
-
"text-classification",
|
| 26 |
-
model=MODEL_PATH,
|
| 27 |
-
tokenizer=MODEL_PATH,
|
| 28 |
-
device=device # Utilise le GPU si disponible
|
| 29 |
-
)
|
| 30 |
-
print("Modèle chargé avec succès !")
|
| 31 |
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
nlu_pipeline = None
|
| 36 |
|
| 37 |
-
# ---
|
| 38 |
app = FastAPI(
|
| 39 |
-
title="
|
| 40 |
-
description="
|
| 41 |
-
version="1.0.0"
|
|
|
|
|
|
|
|
|
|
| 42 |
)
|
| 43 |
|
| 44 |
-
# ---
|
| 45 |
-
# C'est pour la validation automatique des requêtes.
|
| 46 |
|
| 47 |
class TextInput(BaseModel):
|
| 48 |
-
"""
|
| 49 |
-
text: str
|
| 50 |
-
# Exemple de requête JSON attendue: {"text": "3afak bghit nchouf lfactura"}
|
| 51 |
|
| 52 |
class PredictionResponse(BaseModel):
|
| 53 |
-
"""
|
| 54 |
-
intent: str
|
| 55 |
-
confidence: float
|
| 56 |
|
| 57 |
-
# ---
|
| 58 |
|
| 59 |
-
@app.get("/", tags=["
|
| 60 |
def read_root() -> Dict[str, str]:
|
| 61 |
-
"""
|
| 62 |
-
return {"message": "
|
| 63 |
-
|
| 64 |
|
| 65 |
-
@app.get("/health", tags=["
|
| 66 |
def health_check() -> Dict[str, str]:
|
| 67 |
-
"""
|
| 68 |
if nlu_pipeline is None:
|
| 69 |
-
raise HTTPException(status_code=
|
| 70 |
return {"status": "ok", "model_status": "loaded"}
|
| 71 |
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
def predict_intent(request: TextInput) -> PredictionResponse:
|
| 75 |
"""
|
| 76 |
-
|
| 77 |
-
Prend un texte en entrée et retourne l'intention prédite et son score de confiance.
|
| 78 |
"""
|
| 79 |
if nlu_pipeline is None:
|
| 80 |
-
raise HTTPException(status_code=503, detail="
|
| 81 |
-
|
| 82 |
-
if not request.text or not request.text.strip():
|
| 83 |
-
raise HTTPException(status_code=400, detail="Le champ 'text' ne peut pas être vide.")
|
| 84 |
|
| 85 |
try:
|
| 86 |
-
#
|
|
|
|
| 87 |
prediction = nlu_pipeline(request.text, top_k=1)[0]
|
| 88 |
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
return PredictionResponse(intent=intent, confidence=confidence)
|
| 95 |
-
|
| 96 |
except Exception as e:
|
| 97 |
-
#
|
| 98 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Darija NLU API - Professional REST API for Moroccan Arabic Sentiment/Intent Classification.
|
| 3 |
+
Powered by MARBERTv2 fine-tuned on Darija.
|
| 4 |
+
"""
|
| 5 |
|
| 6 |
+
import os
|
| 7 |
+
from contextlib import asynccontextmanager
|
|
|
|
|
|
|
| 8 |
from typing import Dict, Any
|
| 9 |
|
| 10 |
+
from fastapi import FastAPI, HTTPException
|
| 11 |
+
from pydantic import BaseModel, Field
|
| 12 |
+
from transformers import pipeline
|
| 13 |
+
|
| 14 |
# --- Configuration ---
|
| 15 |
+
MODEL_ID = "mediani/marbert-fine-tuned-darija-aicc"
|
|
|
|
| 16 |
|
| 17 |
+
# Global pipeline variable
|
| 18 |
+
nlu_pipeline = None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
+
@asynccontextmanager
|
| 21 |
+
async def lifespan(app: FastAPI):
|
| 22 |
+
"""
|
| 23 |
+
Lifespan context manager for loading the model on startup.
|
| 24 |
+
This ensures the model is loaded only once.
|
| 25 |
+
"""
|
| 26 |
+
global nlu_pipeline
|
| 27 |
+
try:
|
| 28 |
+
print(f"Loading model from HuggingFace Hub: {MODEL_ID}...")
|
| 29 |
+
# device=0 uses GPU if available, -1 uses CPU
|
| 30 |
+
# We rely on transformers to auto-detect the best available device if not specified,
|
| 31 |
+
# but explicit integer is often safer for pipelines.
|
| 32 |
+
import torch
|
| 33 |
+
device = 0 if torch.cuda.is_available() else -1
|
| 34 |
+
|
| 35 |
+
nlu_pipeline = pipeline(
|
| 36 |
+
"text-classification",
|
| 37 |
+
model=MODEL_ID,
|
| 38 |
+
tokenizer=MODEL_ID,
|
| 39 |
+
device=device
|
| 40 |
+
)
|
| 41 |
+
print("Model loaded successfully!")
|
| 42 |
+
except Exception as e:
|
| 43 |
+
print(f"CRITICAL: Failed to load model: {e}")
|
| 44 |
+
nlu_pipeline = None
|
| 45 |
+
yield
|
| 46 |
+
# Cleanup if necessary
|
| 47 |
nlu_pipeline = None
|
| 48 |
|
| 49 |
+
# --- FastAPI App Definition ---
|
| 50 |
app = FastAPI(
|
| 51 |
+
title="Darija NLU API",
|
| 52 |
+
description="Professional API for intent classification in Moroccan Darija (Arabic Dialect).",
|
| 53 |
+
version="1.0.0",
|
| 54 |
+
lifespan=lifespan,
|
| 55 |
+
docs_url="/docs",
|
| 56 |
+
redoc_url="/redoc"
|
| 57 |
)
|
| 58 |
|
| 59 |
+
# --- Data Models ---
|
|
|
|
| 60 |
|
| 61 |
class TextInput(BaseModel):
|
| 62 |
+
"""Request model for text classification."""
|
| 63 |
+
text: str = Field(..., description="The text in Darija to analyze", min_length=1, example="3afak bghit nchouf solde")
|
|
|
|
| 64 |
|
| 65 |
class PredictionResponse(BaseModel):
|
| 66 |
+
"""Response model containing the predicted intent and confidence score."""
|
| 67 |
+
intent: str = Field(..., description="Predicted intent label")
|
| 68 |
+
confidence: float = Field(..., description="Confidence score between 0.0 and 1.0")
|
| 69 |
|
| 70 |
+
# --- Routes ---
|
| 71 |
|
| 72 |
+
@app.get("/", tags=["General"])
|
| 73 |
def read_root() -> Dict[str, str]:
|
| 74 |
+
"""Root endpoint returning welcome message."""
|
| 75 |
+
return {"message": "Welcome to the Darija NLU API. Use POST /predict to analyze text."}
|
|
|
|
| 76 |
|
| 77 |
+
@app.get("/health", tags=["General"])
|
| 78 |
def health_check() -> Dict[str, str]:
|
| 79 |
+
"""Health check endpoint to verify service status and model loading."""
|
| 80 |
if nlu_pipeline is None:
|
| 81 |
+
raise HTTPException(status_code=503, detail="Service initializing or model failed to load.")
|
| 82 |
return {"status": "ok", "model_status": "loaded"}
|
| 83 |
|
| 84 |
+
@app.post("/predict", response_model=PredictionResponse, tags=["Inference"])
|
| 85 |
+
async def predict_intent(request: TextInput) -> PredictionResponse:
|
|
|
|
| 86 |
"""
|
| 87 |
+
Predict the intent of the provided Darija text.
|
|
|
|
| 88 |
"""
|
| 89 |
if nlu_pipeline is None:
|
| 90 |
+
raise HTTPException(status_code=503, detail="Model not initialized.")
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
try:
|
| 93 |
+
# Pipeline returns a list of dicts: [{'label': 'intent_name', 'score': 0.99}]
|
| 94 |
+
# We assume top_k=1 by default
|
| 95 |
prediction = nlu_pipeline(request.text, top_k=1)[0]
|
| 96 |
|
| 97 |
+
return PredictionResponse(
|
| 98 |
+
intent=prediction['label'],
|
| 99 |
+
confidence=prediction['score']
|
| 100 |
+
)
|
|
|
|
|
|
|
|
|
|
| 101 |
except Exception as e:
|
| 102 |
+
# Log the error internally here
|
| 103 |
+
print(f"Inference error: {e}")
|
| 104 |
+
raise HTTPException(status_code=500, detail="Internal processing error")
|
| 105 |
+
|
| 106 |
+
if __name__ == "__main__":
|
| 107 |
+
import uvicorn
|
| 108 |
+
uvicorn.run(app, host="0.0.0.0", port=7860) # 7860 is the default port for HF Spaces
|
mon_modele_darija_final/config.json
DELETED
|
@@ -1,54 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"BertForSequenceClassification"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"classifier_dropout": null,
|
| 7 |
-
"directionality": "bidi",
|
| 8 |
-
"gradient_checkpointing": false,
|
| 9 |
-
"hidden_act": "gelu",
|
| 10 |
-
"hidden_dropout_prob": 0.1,
|
| 11 |
-
"hidden_size": 768,
|
| 12 |
-
"id2label": {
|
| 13 |
-
"0": "consulter_solde",
|
| 14 |
-
"1": "declarer_panne",
|
| 15 |
-
"2": "demander_agent_humain",
|
| 16 |
-
"3": "hors_scope",
|
| 17 |
-
"4": "info_forfait",
|
| 18 |
-
"5": "reclamer_facture",
|
| 19 |
-
"6": "recuperer_mot_de_passe",
|
| 20 |
-
"7": "remerciements",
|
| 21 |
-
"8": "salutations"
|
| 22 |
-
},
|
| 23 |
-
"initializer_range": 0.02,
|
| 24 |
-
"intermediate_size": 3072,
|
| 25 |
-
"label2id": {
|
| 26 |
-
"consulter_solde": 0,
|
| 27 |
-
"declarer_panne": 1,
|
| 28 |
-
"demander_agent_humain": 2,
|
| 29 |
-
"hors_scope": 3,
|
| 30 |
-
"info_forfait": 4,
|
| 31 |
-
"reclamer_facture": 5,
|
| 32 |
-
"recuperer_mot_de_passe": 6,
|
| 33 |
-
"remerciements": 7,
|
| 34 |
-
"salutations": 8
|
| 35 |
-
},
|
| 36 |
-
"layer_norm_eps": 1e-12,
|
| 37 |
-
"max_position_embeddings": 512,
|
| 38 |
-
"model_type": "bert",
|
| 39 |
-
"num_attention_heads": 12,
|
| 40 |
-
"num_hidden_layers": 12,
|
| 41 |
-
"pad_token_id": 0,
|
| 42 |
-
"pooler_fc_size": 768,
|
| 43 |
-
"pooler_num_attention_heads": 12,
|
| 44 |
-
"pooler_num_fc_layers": 3,
|
| 45 |
-
"pooler_size_per_head": 128,
|
| 46 |
-
"pooler_type": "first_token_transform",
|
| 47 |
-
"position_embedding_type": "absolute",
|
| 48 |
-
"problem_type": "single_label_classification",
|
| 49 |
-
"torch_dtype": "float32",
|
| 50 |
-
"transformers_version": "4.52.4",
|
| 51 |
-
"type_vocab_size": 2,
|
| 52 |
-
"use_cache": true,
|
| 53 |
-
"vocab_size": 100000
|
| 54 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mon_modele_darija_final/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:08322d4ab747d8187518d1d649c0bd36e7592fe4224f6b9885c3d2abe821d689
|
| 3 |
-
size 651416604
|
|
|
|
|
|
|
|
|
|
|
|
mon_modele_darija_final/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mon_modele_darija_final/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mon_modele_darija_final/tokenizer_config.json
DELETED
|
@@ -1,58 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "[PAD]",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"clean_up_tokenization_spaces": true,
|
| 45 |
-
"cls_token": "[CLS]",
|
| 46 |
-
"do_basic_tokenize": true,
|
| 47 |
-
"do_lower_case": true,
|
| 48 |
-
"extra_special_tokens": {},
|
| 49 |
-
"mask_token": "[MASK]",
|
| 50 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
-
"never_split": null,
|
| 52 |
-
"pad_token": "[PAD]",
|
| 53 |
-
"sep_token": "[SEP]",
|
| 54 |
-
"strip_accents": null,
|
| 55 |
-
"tokenize_chinese_chars": true,
|
| 56 |
-
"tokenizer_class": "BertTokenizer",
|
| 57 |
-
"unk_token": "[UNK]"
|
| 58 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
mon_modele_darija_final/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1bd13abe00ada94ffbf7c954ed271cc6b814dccf8eb05202ad4977182cdba021
|
| 3 |
-
size 5304
|
|
|
|
|
|
|
|
|
|
|
|
mon_modele_darija_final/vocab.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
requirements.txt
CHANGED
|
@@ -1,14 +1,7 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
# mais pour une image Docker déterministe, la figer est une option.
|
| 9 |
-
torch==2.7.1
|
| 10 |
-
transformers==4.52.4
|
| 11 |
-
|
| 12 |
-
# ---- FastAPI Specific ----
|
| 13 |
-
# Nécessaire pour gérer les formulaires et le téléversement de fichiers, bonne pratique.
|
| 14 |
-
python-multipart
|
|
|
|
| 1 |
+
fastapi>=0.68.0
|
| 2 |
+
uvicorn>=0.15.0
|
| 3 |
+
torch>=1.9.0
|
| 4 |
+
transformers>=4.10.0
|
| 5 |
+
pydantic>=1.8.0
|
| 6 |
+
sentencepiece
|
| 7 |
+
protobuf
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|