cognitive core loading framework
Browse files- README.md +161 -5
- __init__.py +86 -0
- cognitive_base.py +272 -0
- cognitive_checkpoint.py +298 -0
- cognitive_training.py +372 -0
- cognitive_utils.py +282 -0
README.md
CHANGED
|
@@ -1,5 +1,161 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# COGNITIVE-CORE Framework
|
| 2 |
+
|
| 3 |
+
> Standard universel pour les architectures cognitives d'Ame Web Studio
|
| 4 |
+
|
| 5 |
+
## 🏗️ Structure
|
| 6 |
+
|
| 7 |
+
```
|
| 8 |
+
cognitive-core/
|
| 9 |
+
├── __init__.py # Exports du package
|
| 10 |
+
├── cognitive_base.py # Classes de base (Config, Modules, PreTrainedModel)
|
| 11 |
+
├── cognitive_checkpoint.py # Chargement/sauvegarde avec remappage auto
|
| 12 |
+
├── cognitive_utils.py # Utilitaires (device, mémoire, tokens)
|
| 13 |
+
└── README.md # Cette documentation
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
## 🚀 Installation
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
# Ajouter à votre modèle
|
| 20 |
+
import sys
|
| 21 |
+
sys.path.append("/path/to/standardisation")
|
| 22 |
+
|
| 23 |
+
from cognitive_core import (
|
| 24 |
+
CognitiveConfig,
|
| 25 |
+
CognitivePreTrainedModel,
|
| 26 |
+
setup_environment,
|
| 27 |
+
get_device
|
| 28 |
+
)
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
## 📖 Guide d'Utilisation
|
| 32 |
+
|
| 33 |
+
### 1. Créer une Configuration
|
| 34 |
+
|
| 35 |
+
```python
|
| 36 |
+
from cognitive_core import CognitiveConfig
|
| 37 |
+
|
| 38 |
+
class MyModelConfig(CognitiveConfig):
|
| 39 |
+
model_type = "my_cognitive_model"
|
| 40 |
+
|
| 41 |
+
def __init__(
|
| 42 |
+
self,
|
| 43 |
+
vocab_size: int = 50000,
|
| 44 |
+
# ... vos paramètres
|
| 45 |
+
**kwargs
|
| 46 |
+
):
|
| 47 |
+
super().__init__(**kwargs)
|
| 48 |
+
self.vocab_size = vocab_size
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
### 2. Créer un Modèle Cognitif
|
| 52 |
+
|
| 53 |
+
```python
|
| 54 |
+
from cognitive_core import CognitivePreTrainedModel, CognitiveModule
|
| 55 |
+
import torch.nn as nn
|
| 56 |
+
|
| 57 |
+
class MyMemoryModule(CognitiveModule):
|
| 58 |
+
def __init__(self, config):
|
| 59 |
+
super().__init__(config)
|
| 60 |
+
self.memory = nn.Parameter(torch.randn(1000, config.d_model))
|
| 61 |
+
|
| 62 |
+
def forward(self, x, **kwargs):
|
| 63 |
+
# Votre logique
|
| 64 |
+
return {"output": x, "memory_used": True}
|
| 65 |
+
|
| 66 |
+
def reset_state(self):
|
| 67 |
+
pass
|
| 68 |
+
|
| 69 |
+
class MyModel(CognitivePreTrainedModel):
|
| 70 |
+
config_class = MyModelConfig
|
| 71 |
+
|
| 72 |
+
def __init__(self, config):
|
| 73 |
+
super().__init__(config)
|
| 74 |
+
self.embeddings = nn.Embedding(config.vocab_size, config.d_model)
|
| 75 |
+
self.memory = MyMemoryModule(config)
|
| 76 |
+
self.lm_head = nn.Linear(config.d_model, config.vocab_size)
|
| 77 |
+
self.post_init()
|
| 78 |
+
|
| 79 |
+
def forward(self, input_ids, **kwargs):
|
| 80 |
+
x = self.embeddings(input_ids)
|
| 81 |
+
mem_out = self.memory(x)
|
| 82 |
+
logits = self.lm_head(mem_out["output"])
|
| 83 |
+
return logits
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
### 3. Chargement Automatique
|
| 87 |
+
|
| 88 |
+
Le framework gère automatiquement:
|
| 89 |
+
- ✅ Remappage des clés (avec/sans préfixe `model.`)
|
| 90 |
+
- ✅ Validation du checkpoint
|
| 91 |
+
- ✅ Compatibilité HuggingFace
|
| 92 |
+
|
| 93 |
+
```python
|
| 94 |
+
from cognitive_core import load_cognitive_checkpoint
|
| 95 |
+
|
| 96 |
+
# Charger un checkpoint personnalisé
|
| 97 |
+
info = load_cognitive_checkpoint(model, "path/to/checkpoint.pt", verbose=True)
|
| 98 |
+
print(f"Clés chargées: {info['validation']['matched_keys']}")
|
| 99 |
+
```
|
| 100 |
+
|
| 101 |
+
### 4. Configuration Environnement (Kaggle/Colab)
|
| 102 |
+
|
| 103 |
+
```python
|
| 104 |
+
from cognitive_core import setup_environment, get_device, get_hf_token
|
| 105 |
+
|
| 106 |
+
# Configure cache HuggingFace dans répertoire accessible
|
| 107 |
+
cache_dir = setup_environment()
|
| 108 |
+
|
| 109 |
+
# Détection automatique GPU/CPU
|
| 110 |
+
device = get_device()
|
| 111 |
+
|
| 112 |
+
# Récupérer token HuggingFace
|
| 113 |
+
token = get_hf_token()
|
| 114 |
+
```
|
| 115 |
+
|
| 116 |
+
## 🔧 Modules Disponibles
|
| 117 |
+
|
| 118 |
+
| Module | Description |
|
| 119 |
+
|--------|-------------|
|
| 120 |
+
| `CognitiveConfig` | Configuration de base héritant de PretrainedConfig |
|
| 121 |
+
| `CognitiveModule` | Interface abstraite pour modules cognitifs |
|
| 122 |
+
| `MemoryModule` | Interface pour modules de mémoire (store/retrieve) |
|
| 123 |
+
| `TemporalModule` | Interface pour modules temporels (predict) |
|
| 124 |
+
| `WorldModelModule` | Interface pour modèles du monde (update/imagine) |
|
| 125 |
+
| `CognitivePreTrainedModel` | Modèle HuggingFace avec remappage auto |
|
| 126 |
+
|
| 127 |
+
## 🎯 Cas d'Usage
|
| 128 |
+
|
| 129 |
+
### Vision Cognitive
|
| 130 |
+
```python
|
| 131 |
+
class CognitiveViTConfig(CognitiveConfig):
|
| 132 |
+
model_type = "cognitive_vit"
|
| 133 |
+
# ... config vision
|
| 134 |
+
```
|
| 135 |
+
|
| 136 |
+
### World Model
|
| 137 |
+
```python
|
| 138 |
+
class CognitiveWorldConfig(CognitiveConfig):
|
| 139 |
+
model_type = "cognitive_world"
|
| 140 |
+
# ... config world model
|
| 141 |
+
```
|
| 142 |
+
|
| 143 |
+
### Multimodal
|
| 144 |
+
```python
|
| 145 |
+
class CognitiveMultimodalConfig(CognitiveConfig):
|
| 146 |
+
model_type = "cognitive_multimodal"
|
| 147 |
+
vision_enabled = True
|
| 148 |
+
audio_enabled = True
|
| 149 |
+
```
|
| 150 |
+
|
| 151 |
+
## 📊 Garanties du Standard
|
| 152 |
+
|
| 153 |
+
- ✅ **Intégrité des poids** - Aucun poids réinitialisé silencieusement
|
| 154 |
+
- ✅ **Compatibilité HuggingFace** - AutoModel fonctionne nativement
|
| 155 |
+
- ✅ **Portabilité** - Kaggle, Colab, Local sans modification
|
| 156 |
+
- ✅ **Extensibilité** - Ajouter vos modules facilement
|
| 157 |
+
|
| 158 |
+
## 📄 Licence
|
| 159 |
+
|
| 160 |
+
**PROPRIETARY - ALL RIGHTS RESERVED**
|
| 161 |
+
Copyright © 2026 Mike Amega (Logo) - Ame Web Studio
|
__init__.py
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
COGNITIVE-CORE Framework
|
| 3 |
+
========================
|
| 4 |
+
|
| 5 |
+
Universal template for Ame Web Studio's cognitive AI architectures.
|
| 6 |
+
Provides standardized loading, checkpoint management, and utilities
|
| 7 |
+
for vision, language, world model, and multimodal cognitive systems.
|
| 8 |
+
|
| 9 |
+
Copyright © 2026 Mike Amega (Logo) - Ame Web Studio
|
| 10 |
+
License: Proprietary - All Rights Reserved
|
| 11 |
+
"""
|
| 12 |
+
|
| 13 |
+
from .cognitive_base import (
|
| 14 |
+
CognitiveConfig,
|
| 15 |
+
CognitiveModule,
|
| 16 |
+
MemoryModule,
|
| 17 |
+
TemporalModule,
|
| 18 |
+
WorldModelModule,
|
| 19 |
+
CognitivePreTrainedModel,
|
| 20 |
+
register_cognitive_model,
|
| 21 |
+
)
|
| 22 |
+
|
| 23 |
+
from .cognitive_checkpoint import (
|
| 24 |
+
remap_checkpoint_keys,
|
| 25 |
+
validate_checkpoint,
|
| 26 |
+
save_cognitive_checkpoint,
|
| 27 |
+
load_cognitive_checkpoint,
|
| 28 |
+
)
|
| 29 |
+
|
| 30 |
+
from .cognitive_utils import (
|
| 31 |
+
setup_environment,
|
| 32 |
+
get_device,
|
| 33 |
+
get_optimal_dtype,
|
| 34 |
+
get_memory_info,
|
| 35 |
+
clear_memory,
|
| 36 |
+
estimate_model_memory,
|
| 37 |
+
print_model_info,
|
| 38 |
+
print_training_progress,
|
| 39 |
+
get_hf_token,
|
| 40 |
+
)
|
| 41 |
+
|
| 42 |
+
from .cognitive_training import (
|
| 43 |
+
CognitiveTrainingConfig,
|
| 44 |
+
CognitiveTrainer,
|
| 45 |
+
prepare_dataset,
|
| 46 |
+
create_instruction_dataset,
|
| 47 |
+
quick_train,
|
| 48 |
+
CognitiveStateCallback,
|
| 49 |
+
)
|
| 50 |
+
|
| 51 |
+
__version__ = "1.0.0"
|
| 52 |
+
__author__ = "Mike Amega"
|
| 53 |
+
__license__ = "Proprietary"
|
| 54 |
+
|
| 55 |
+
__all__ = [
|
| 56 |
+
# Base classes
|
| 57 |
+
"CognitiveConfig",
|
| 58 |
+
"CognitiveModule",
|
| 59 |
+
"MemoryModule",
|
| 60 |
+
"TemporalModule",
|
| 61 |
+
"WorldModelModule",
|
| 62 |
+
"CognitivePreTrainedModel",
|
| 63 |
+
"register_cognitive_model",
|
| 64 |
+
# Checkpoint
|
| 65 |
+
"remap_checkpoint_keys",
|
| 66 |
+
"validate_checkpoint",
|
| 67 |
+
"save_cognitive_checkpoint",
|
| 68 |
+
"load_cognitive_checkpoint",
|
| 69 |
+
# Utils
|
| 70 |
+
"setup_environment",
|
| 71 |
+
"get_device",
|
| 72 |
+
"get_optimal_dtype",
|
| 73 |
+
"get_memory_info",
|
| 74 |
+
"clear_memory",
|
| 75 |
+
"estimate_model_memory",
|
| 76 |
+
"print_model_info",
|
| 77 |
+
"print_training_progress",
|
| 78 |
+
"get_hf_token",
|
| 79 |
+
# Training
|
| 80 |
+
"CognitiveTrainingConfig",
|
| 81 |
+
"CognitiveTrainer",
|
| 82 |
+
"prepare_dataset",
|
| 83 |
+
"create_instruction_dataset",
|
| 84 |
+
"quick_train",
|
| 85 |
+
"CognitiveStateCallback",
|
| 86 |
+
]
|
cognitive_base.py
ADDED
|
@@ -0,0 +1,272 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
COGNITIVE-CORE: Base Classes for Cognitive Architectures
|
| 3 |
+
=========================================================
|
| 4 |
+
|
| 5 |
+
This module provides the foundational classes for building cognitive AI models
|
| 6 |
+
that follow the Ame Web Studio standard. All cognitive models (vision, language,
|
| 7 |
+
world model, multimodal) should inherit from these base classes.
|
| 8 |
+
|
| 9 |
+
Copyright © 2026 Mike Amega (Logo) - Ame Web Studio
|
| 10 |
+
License: Proprietary - All Rights Reserved
|
| 11 |
+
"""
|
| 12 |
+
|
| 13 |
+
import torch
|
| 14 |
+
import torch.nn as nn
|
| 15 |
+
from typing import Dict, List, Optional, Any, Tuple
|
| 16 |
+
from abc import ABC, abstractmethod
|
| 17 |
+
|
| 18 |
+
from transformers import PreTrainedModel, PretrainedConfig
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
# ==============================================================================
|
| 22 |
+
# CONFIGURATION DE BASE
|
| 23 |
+
# ==============================================================================
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
class CognitiveConfig(PretrainedConfig):
|
| 27 |
+
"""
|
| 28 |
+
Configuration de base pour tous les modèles cognitifs.
|
| 29 |
+
|
| 30 |
+
Tous les modèles cognitifs (vision, language, world, multimodal) doivent
|
| 31 |
+
hériter de cette configuration pour garantir la compatibilité.
|
| 32 |
+
"""
|
| 33 |
+
|
| 34 |
+
model_type = "cognitive"
|
| 35 |
+
|
| 36 |
+
def __init__(
|
| 37 |
+
self,
|
| 38 |
+
# Dimensions de base
|
| 39 |
+
d_model: int = 512,
|
| 40 |
+
d_ff: int = 2048,
|
| 41 |
+
n_layers: int = 12,
|
| 42 |
+
n_heads: int = 8,
|
| 43 |
+
dropout: float = 0.1,
|
| 44 |
+
# Modules cognitifs (peuvent être activés/désactivés)
|
| 45 |
+
use_memory: bool = True,
|
| 46 |
+
use_temporal: bool = True,
|
| 47 |
+
use_synaptic: bool = True,
|
| 48 |
+
use_dream: bool = True,
|
| 49 |
+
use_world_model: bool = True,
|
| 50 |
+
use_neurogenesis: bool = True,
|
| 51 |
+
# Mémoire
|
| 52 |
+
memory_size: int = 8192,
|
| 53 |
+
short_term_dim: int = 512,
|
| 54 |
+
long_term_dim: int = 256,
|
| 55 |
+
# États internes
|
| 56 |
+
internal_state_dim: int = 128,
|
| 57 |
+
latent_state_dim: int = 768,
|
| 58 |
+
# Meta
|
| 59 |
+
version: str = "1.0",
|
| 60 |
+
author: str = "Mike Amega",
|
| 61 |
+
license: str = "Proprietary",
|
| 62 |
+
**kwargs,
|
| 63 |
+
):
|
| 64 |
+
super().__init__(**kwargs)
|
| 65 |
+
|
| 66 |
+
# Dimensions
|
| 67 |
+
self.d_model = d_model
|
| 68 |
+
self.hidden_size = d_model # Alias HuggingFace
|
| 69 |
+
self.d_ff = d_ff
|
| 70 |
+
self.n_layers = n_layers
|
| 71 |
+
self.n_heads = n_heads
|
| 72 |
+
self.dropout = dropout
|
| 73 |
+
|
| 74 |
+
# Modules cognitifs
|
| 75 |
+
self.use_memory = use_memory
|
| 76 |
+
self.use_temporal = use_temporal
|
| 77 |
+
self.use_synaptic = use_synaptic
|
| 78 |
+
self.use_dream = use_dream
|
| 79 |
+
self.use_world_model = use_world_model
|
| 80 |
+
self.use_neurogenesis = use_neurogenesis
|
| 81 |
+
|
| 82 |
+
# Mémoire
|
| 83 |
+
self.memory_size = memory_size
|
| 84 |
+
self.short_term_dim = short_term_dim
|
| 85 |
+
self.long_term_dim = long_term_dim
|
| 86 |
+
|
| 87 |
+
# États
|
| 88 |
+
self.internal_state_dim = internal_state_dim
|
| 89 |
+
self.latent_state_dim = latent_state_dim
|
| 90 |
+
|
| 91 |
+
# Meta
|
| 92 |
+
self.version = version
|
| 93 |
+
self.author = author
|
| 94 |
+
self.license = license
|
| 95 |
+
|
| 96 |
+
@property
|
| 97 |
+
def head_dim(self) -> int:
|
| 98 |
+
return self.d_model // self.n_heads
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
# ==============================================================================
|
| 102 |
+
# MODULES COGNITIFS ABSTRAITS
|
| 103 |
+
# ==============================================================================
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
class CognitiveModule(nn.Module, ABC):
|
| 107 |
+
"""
|
| 108 |
+
Classe de base abstraite pour tous les modules cognitifs.
|
| 109 |
+
|
| 110 |
+
Chaque module cognitif doit implémenter:
|
| 111 |
+
- forward(): traitement principal
|
| 112 |
+
- reset_state(): réinitialisation des états internes
|
| 113 |
+
- get_state(): récupérer l'état courant
|
| 114 |
+
"""
|
| 115 |
+
|
| 116 |
+
def __init__(self, config: CognitiveConfig):
|
| 117 |
+
super().__init__()
|
| 118 |
+
self.config = config
|
| 119 |
+
|
| 120 |
+
@abstractmethod
|
| 121 |
+
def forward(self, x: torch.Tensor, **kwargs) -> Dict[str, Any]:
|
| 122 |
+
"""Traitement principal du module."""
|
| 123 |
+
pass
|
| 124 |
+
|
| 125 |
+
@abstractmethod
|
| 126 |
+
def reset_state(self):
|
| 127 |
+
"""Réinitialiser les états internes du module."""
|
| 128 |
+
pass
|
| 129 |
+
|
| 130 |
+
def get_state(self) -> Dict[str, torch.Tensor]:
|
| 131 |
+
"""Récupérer l'état courant (pour sauvegarde/debug)."""
|
| 132 |
+
return {}
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
class MemoryModule(CognitiveModule):
|
| 136 |
+
"""Interface pour les modules de mémoire."""
|
| 137 |
+
|
| 138 |
+
@abstractmethod
|
| 139 |
+
def store(self, key: torch.Tensor, value: torch.Tensor):
|
| 140 |
+
"""Stocker une information en mémoire."""
|
| 141 |
+
pass
|
| 142 |
+
|
| 143 |
+
@abstractmethod
|
| 144 |
+
def retrieve(self, query: torch.Tensor, k: int = 1) -> torch.Tensor:
|
| 145 |
+
"""Récupérer les k informations les plus pertinentes."""
|
| 146 |
+
pass
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
class TemporalModule(CognitiveModule):
|
| 150 |
+
"""Interface pour les modules temporels/prédictifs."""
|
| 151 |
+
|
| 152 |
+
@abstractmethod
|
| 153 |
+
def predict(self, state: torch.Tensor, horizon: int = 1) -> torch.Tensor:
|
| 154 |
+
"""Prédire l'état futur à l'horizon donné."""
|
| 155 |
+
pass
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
class WorldModelModule(CognitiveModule):
|
| 159 |
+
"""Interface pour les modèles du monde."""
|
| 160 |
+
|
| 161 |
+
@abstractmethod
|
| 162 |
+
def update(self, observation: torch.Tensor) -> Dict[str, float]:
|
| 163 |
+
"""Mettre à jour le modèle du monde avec une observation."""
|
| 164 |
+
pass
|
| 165 |
+
|
| 166 |
+
@abstractmethod
|
| 167 |
+
def imagine(self, action: torch.Tensor) -> torch.Tensor:
|
| 168 |
+
"""Imaginer l'effet d'une action."""
|
| 169 |
+
pass
|
| 170 |
+
|
| 171 |
+
|
| 172 |
+
# ==============================================================================
|
| 173 |
+
# MODÈLE COGNITIF DE BASE
|
| 174 |
+
# ==============================================================================
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
class CognitivePreTrainedModel(PreTrainedModel):
|
| 178 |
+
"""
|
| 179 |
+
Classe de base pour tous les modèles cognitifs HuggingFace-compatibles.
|
| 180 |
+
|
| 181 |
+
Fournit:
|
| 182 |
+
- Remappage automatique des clés de checkpoint
|
| 183 |
+
- Gestion des modules cognitifs optionnels
|
| 184 |
+
- Méthodes d'initialisation standardisées
|
| 185 |
+
"""
|
| 186 |
+
|
| 187 |
+
config_class = CognitiveConfig
|
| 188 |
+
base_model_prefix = "cognitive"
|
| 189 |
+
supports_gradient_checkpointing = False # Incompatible avec architecture cognitive
|
| 190 |
+
|
| 191 |
+
# Clés à ignorer lors du chargement (buffers dynamiques)
|
| 192 |
+
_keys_to_ignore_on_load_missing = [
|
| 193 |
+
r".*\.state$",
|
| 194 |
+
r".*\.history$",
|
| 195 |
+
r".*\.buffer$",
|
| 196 |
+
r".*rope\..*_cache",
|
| 197 |
+
r".*rope\.inv_freq",
|
| 198 |
+
]
|
| 199 |
+
|
| 200 |
+
def _init_weights(self, module):
|
| 201 |
+
"""Initialisation standard des poids."""
|
| 202 |
+
if isinstance(module, nn.Linear):
|
| 203 |
+
torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
|
| 204 |
+
if module.bias is not None:
|
| 205 |
+
torch.nn.init.zeros_(module.bias)
|
| 206 |
+
elif isinstance(module, nn.Embedding):
|
| 207 |
+
torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
|
| 208 |
+
|
| 209 |
+
def _load_from_state_dict(
|
| 210 |
+
self,
|
| 211 |
+
state_dict,
|
| 212 |
+
prefix,
|
| 213 |
+
local_metadata,
|
| 214 |
+
strict,
|
| 215 |
+
missing_keys,
|
| 216 |
+
unexpected_keys,
|
| 217 |
+
error_msgs,
|
| 218 |
+
):
|
| 219 |
+
"""
|
| 220 |
+
Remappage automatique des clés de checkpoint.
|
| 221 |
+
|
| 222 |
+
Gère les différences de préfixes entre formats de checkpoint
|
| 223 |
+
(ex: avec/sans 'model.' prefix).
|
| 224 |
+
"""
|
| 225 |
+
from .cognitive_checkpoint import remap_checkpoint_keys
|
| 226 |
+
|
| 227 |
+
# Remapper les clés si nécessaire
|
| 228 |
+
remapped = remap_checkpoint_keys(state_dict, self.state_dict())
|
| 229 |
+
|
| 230 |
+
# Appeler l'implémentation parent
|
| 231 |
+
super()._load_from_state_dict(
|
| 232 |
+
remapped,
|
| 233 |
+
prefix,
|
| 234 |
+
local_metadata,
|
| 235 |
+
strict,
|
| 236 |
+
missing_keys,
|
| 237 |
+
unexpected_keys,
|
| 238 |
+
error_msgs,
|
| 239 |
+
)
|
| 240 |
+
|
| 241 |
+
def get_cognitive_state(self) -> Dict[str, Any]:
|
| 242 |
+
"""Récupérer l'état de tous les modules cognitifs."""
|
| 243 |
+
state = {}
|
| 244 |
+
for name, module in self.named_modules():
|
| 245 |
+
if isinstance(module, CognitiveModule):
|
| 246 |
+
state[name] = module.get_state()
|
| 247 |
+
return state
|
| 248 |
+
|
| 249 |
+
def reset_cognitive_state(self):
|
| 250 |
+
"""Réinitialiser l'état de tous les modules cognitifs."""
|
| 251 |
+
for module in self.modules():
|
| 252 |
+
if isinstance(module, CognitiveModule):
|
| 253 |
+
module.reset_state()
|
| 254 |
+
|
| 255 |
+
|
| 256 |
+
# ==============================================================================
|
| 257 |
+
# UTILITAIRES D'ENREGISTREMENT AUTO
|
| 258 |
+
# ==============================================================================
|
| 259 |
+
|
| 260 |
+
|
| 261 |
+
def register_cognitive_model(config_class, model_class):
|
| 262 |
+
"""
|
| 263 |
+
Enregistrer un modèle cognitif pour utilisation avec AutoModel.
|
| 264 |
+
|
| 265 |
+
Usage:
|
| 266 |
+
register_cognitive_model(MyConfig, MyModel)
|
| 267 |
+
# Puis: AutoModelForCausalLM.from_pretrained(..., trust_remote_code=True)
|
| 268 |
+
"""
|
| 269 |
+
from transformers import AutoConfig, AutoModel
|
| 270 |
+
|
| 271 |
+
AutoConfig.register(config_class.model_type, config_class)
|
| 272 |
+
AutoModel.register(config_class, model_class)
|
cognitive_checkpoint.py
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
COGNITIVE-CORE: Checkpoint Loading & Key Remapping
|
| 3 |
+
===================================================
|
| 4 |
+
|
| 5 |
+
This module provides robust checkpoint loading with automatic key remapping
|
| 6 |
+
to handle different checkpoint formats (with/without 'model.' prefix, etc.)
|
| 7 |
+
|
| 8 |
+
Copyright © 2026 Mike Amega (Logo) - Ame Web Studio
|
| 9 |
+
License: Proprietary - All Rights Reserved
|
| 10 |
+
"""
|
| 11 |
+
|
| 12 |
+
import re
|
| 13 |
+
from typing import Dict, Set, Optional
|
| 14 |
+
import torch
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
def remap_checkpoint_keys(
|
| 18 |
+
checkpoint_state_dict: Dict[str, torch.Tensor],
|
| 19 |
+
model_state_dict: Dict[str, torch.Tensor],
|
| 20 |
+
verbose: bool = False,
|
| 21 |
+
) -> Dict[str, torch.Tensor]:
|
| 22 |
+
"""
|
| 23 |
+
Remappe automatiquement les clés du checkpoint pour correspondre au modèle.
|
| 24 |
+
|
| 25 |
+
Gère les scénarios suivants:
|
| 26 |
+
1. Checkpoint a préfixe 'model.' mais modèle n'en a pas → retirer préfixe
|
| 27 |
+
2. Checkpoint n'a pas préfixe 'model.' mais modèle en a → ajouter préfixe
|
| 28 |
+
3. Autres préfixes personnalisés
|
| 29 |
+
|
| 30 |
+
Args:
|
| 31 |
+
checkpoint_state_dict: État du checkpoint chargé
|
| 32 |
+
model_state_dict: État du modèle cible
|
| 33 |
+
verbose: Afficher les détails du remappage
|
| 34 |
+
|
| 35 |
+
Returns:
|
| 36 |
+
Dict remappé compatible avec le modèle
|
| 37 |
+
"""
|
| 38 |
+
model_keys = set(model_state_dict.keys())
|
| 39 |
+
checkpoint_keys = set(checkpoint_state_dict.keys())
|
| 40 |
+
|
| 41 |
+
# Vérifier si le checkpoint correspond déjà
|
| 42 |
+
matching = model_keys & checkpoint_keys
|
| 43 |
+
if len(matching) >= len(checkpoint_keys) * 0.9:
|
| 44 |
+
if verbose:
|
| 45 |
+
print(
|
| 46 |
+
f"✅ Checkpoint compatible: {len(matching)}/{len(checkpoint_keys)} clés correspondent"
|
| 47 |
+
)
|
| 48 |
+
return checkpoint_state_dict
|
| 49 |
+
|
| 50 |
+
# Tester différentes stratégies de remappage
|
| 51 |
+
strategies = [
|
| 52 |
+
("remove_model_prefix", _remove_prefix, "model."),
|
| 53 |
+
("add_model_prefix", _add_prefix, "model."),
|
| 54 |
+
("remove_backbone_prefix", _remove_prefix, "backbone."),
|
| 55 |
+
("remove_encoder_prefix", _remove_prefix, "encoder."),
|
| 56 |
+
]
|
| 57 |
+
|
| 58 |
+
best_strategy = None
|
| 59 |
+
best_match_count = len(matching)
|
| 60 |
+
best_result = checkpoint_state_dict
|
| 61 |
+
|
| 62 |
+
for name, func, prefix in strategies:
|
| 63 |
+
remapped = func(checkpoint_state_dict, prefix)
|
| 64 |
+
match_count = len(model_keys & set(remapped.keys()))
|
| 65 |
+
|
| 66 |
+
if match_count > best_match_count:
|
| 67 |
+
best_match_count = match_count
|
| 68 |
+
best_strategy = name
|
| 69 |
+
best_result = remapped
|
| 70 |
+
|
| 71 |
+
if verbose and best_strategy:
|
| 72 |
+
print(f"🔄 Stratégie appliquée: {best_strategy}")
|
| 73 |
+
print(f" Clés correspondantes: {best_match_count}/{len(checkpoint_keys)}")
|
| 74 |
+
|
| 75 |
+
# Fallback: mapper intelligemment clé par clé
|
| 76 |
+
if best_match_count < len(checkpoint_keys) * 0.5:
|
| 77 |
+
best_result = _smart_key_mapping(checkpoint_state_dict, model_keys)
|
| 78 |
+
if verbose:
|
| 79 |
+
final_match = len(model_keys & set(best_result.keys()))
|
| 80 |
+
print(
|
| 81 |
+
f"🧠 Remappage intelligent: {final_match}/{len(checkpoint_keys)} clés"
|
| 82 |
+
)
|
| 83 |
+
|
| 84 |
+
return best_result
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def _remove_prefix(state_dict: Dict, prefix: str) -> Dict:
|
| 88 |
+
"""Retirer un préfixe de toutes les clés."""
|
| 89 |
+
return {
|
| 90 |
+
(k[len(prefix) :] if k.startswith(prefix) else k): v
|
| 91 |
+
for k, v in state_dict.items()
|
| 92 |
+
}
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def _add_prefix(state_dict: Dict, prefix: str) -> Dict:
|
| 96 |
+
"""Ajouter un préfixe à toutes les clés."""
|
| 97 |
+
return {f"{prefix}{k}": v for k, v in state_dict.items()}
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
def _smart_key_mapping(
|
| 101 |
+
checkpoint_dict: Dict[str, torch.Tensor], model_keys: Set[str]
|
| 102 |
+
) -> Dict[str, torch.Tensor]:
|
| 103 |
+
"""
|
| 104 |
+
Mapping intelligent clé par clé basé sur les suffixes et patterns.
|
| 105 |
+
"""
|
| 106 |
+
result = {}
|
| 107 |
+
model_keys_list = list(model_keys)
|
| 108 |
+
|
| 109 |
+
for ckpt_key, value in checkpoint_dict.items():
|
| 110 |
+
# Correspondance exacte
|
| 111 |
+
if ckpt_key in model_keys:
|
| 112 |
+
result[ckpt_key] = value
|
| 113 |
+
continue
|
| 114 |
+
|
| 115 |
+
# Essayer avec préfixe 'model.'
|
| 116 |
+
with_prefix = f"model.{ckpt_key}"
|
| 117 |
+
if with_prefix in model_keys:
|
| 118 |
+
result[with_prefix] = value
|
| 119 |
+
continue
|
| 120 |
+
|
| 121 |
+
# Essayer sans préfixe 'model.'
|
| 122 |
+
if ckpt_key.startswith("model."):
|
| 123 |
+
without_prefix = ckpt_key[6:]
|
| 124 |
+
if without_prefix in model_keys:
|
| 125 |
+
result[without_prefix] = value
|
| 126 |
+
continue
|
| 127 |
+
|
| 128 |
+
# Chercher par suffixe (ex: ".weight", ".bias")
|
| 129 |
+
ckpt_suffix = ckpt_key.split(".")[-1]
|
| 130 |
+
ckpt_base = ".".join(ckpt_key.split(".")[:-1])
|
| 131 |
+
|
| 132 |
+
for model_key in model_keys_list:
|
| 133 |
+
if model_key.endswith(ckpt_suffix):
|
| 134 |
+
model_base = ".".join(model_key.split(".")[:-1])
|
| 135 |
+
# Vérifier similarité structurelle
|
| 136 |
+
if _keys_similar(ckpt_base, model_base):
|
| 137 |
+
result[model_key] = value
|
| 138 |
+
break
|
| 139 |
+
else:
|
| 140 |
+
# Garder la clé originale (sera ignorée si pas dans modèle)
|
| 141 |
+
result[ckpt_key] = value
|
| 142 |
+
|
| 143 |
+
return result
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
def _keys_similar(key1: str, key2: str) -> bool:
|
| 147 |
+
"""Vérifier si deux clés sont structurellement similaires."""
|
| 148 |
+
parts1 = key1.split(".")
|
| 149 |
+
parts2 = key2.split(".")
|
| 150 |
+
|
| 151 |
+
# Même nombre de parties
|
| 152 |
+
if len(parts1) != len(parts2):
|
| 153 |
+
return False
|
| 154 |
+
|
| 155 |
+
# Comparer chaque partie (ignorer les préfixes comme 'model')
|
| 156 |
+
matches = sum(
|
| 157 |
+
1 for p1, p2 in zip(parts1, parts2) if p1 == p2 or p1.isdigit() and p2.isdigit()
|
| 158 |
+
)
|
| 159 |
+
return matches >= len(parts1) * 0.7
|
| 160 |
+
|
| 161 |
+
|
| 162 |
+
def validate_checkpoint(
|
| 163 |
+
checkpoint_state_dict: Dict[str, torch.Tensor],
|
| 164 |
+
model_state_dict: Dict[str, torch.Tensor],
|
| 165 |
+
strict: bool = False,
|
| 166 |
+
) -> Dict[str, any]:
|
| 167 |
+
"""
|
| 168 |
+
Valider qu'un checkpoint est compatible avec un modèle.
|
| 169 |
+
|
| 170 |
+
Returns:
|
| 171 |
+
Dict avec:
|
| 172 |
+
- valid: bool
|
| 173 |
+
- missing_keys: clés manquantes dans checkpoint
|
| 174 |
+
- unexpected_keys: clés inattendues dans checkpoint
|
| 175 |
+
- size_mismatches: clés avec tailles incompatibles
|
| 176 |
+
"""
|
| 177 |
+
model_keys = set(model_state_dict.keys())
|
| 178 |
+
ckpt_keys = set(checkpoint_state_dict.keys())
|
| 179 |
+
|
| 180 |
+
missing = model_keys - ckpt_keys
|
| 181 |
+
unexpected = ckpt_keys - model_keys
|
| 182 |
+
|
| 183 |
+
# Vérifier les tailles
|
| 184 |
+
size_mismatches = []
|
| 185 |
+
for key in model_keys & ckpt_keys:
|
| 186 |
+
model_shape = model_state_dict[key].shape
|
| 187 |
+
ckpt_shape = checkpoint_state_dict[key].shape
|
| 188 |
+
if model_shape != ckpt_shape:
|
| 189 |
+
size_mismatches.append(
|
| 190 |
+
{"key": key, "model_shape": model_shape, "checkpoint_shape": ckpt_shape}
|
| 191 |
+
)
|
| 192 |
+
|
| 193 |
+
valid = len(missing) == 0 and len(size_mismatches) == 0
|
| 194 |
+
if not strict:
|
| 195 |
+
valid = len(size_mismatches) == 0 and len(missing) < len(model_keys) * 0.1
|
| 196 |
+
|
| 197 |
+
return {
|
| 198 |
+
"valid": valid,
|
| 199 |
+
"missing_keys": list(missing),
|
| 200 |
+
"unexpected_keys": list(unexpected),
|
| 201 |
+
"size_mismatches": size_mismatches,
|
| 202 |
+
"matched_keys": len(model_keys & ckpt_keys),
|
| 203 |
+
"total_model_keys": len(model_keys),
|
| 204 |
+
}
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
def save_cognitive_checkpoint(
|
| 208 |
+
model,
|
| 209 |
+
path: str,
|
| 210 |
+
include_optimizer: bool = False,
|
| 211 |
+
optimizer=None,
|
| 212 |
+
extra_state: Optional[Dict] = None,
|
| 213 |
+
):
|
| 214 |
+
"""
|
| 215 |
+
Sauvegarder un checkpoint de modèle cognitif.
|
| 216 |
+
|
| 217 |
+
Args:
|
| 218 |
+
model: Le modèle à sauvegarder
|
| 219 |
+
path: Chemin de sauvegarde
|
| 220 |
+
include_optimizer: Inclure l'état de l'optimiseur
|
| 221 |
+
optimizer: L'optimiseur (si include_optimizer=True)
|
| 222 |
+
extra_state: État additionnel à sauvegarder
|
| 223 |
+
"""
|
| 224 |
+
checkpoint = {
|
| 225 |
+
"model_state_dict": model.state_dict(),
|
| 226 |
+
"config": model.config.to_dict() if hasattr(model, "config") else {},
|
| 227 |
+
}
|
| 228 |
+
|
| 229 |
+
if include_optimizer and optimizer is not None:
|
| 230 |
+
checkpoint["optimizer_state_dict"] = optimizer.state_dict()
|
| 231 |
+
|
| 232 |
+
# Sauvegarder l'état cognitif si disponible
|
| 233 |
+
if hasattr(model, "get_cognitive_state"):
|
| 234 |
+
checkpoint["cognitive_state"] = model.get_cognitive_state()
|
| 235 |
+
|
| 236 |
+
if extra_state:
|
| 237 |
+
checkpoint["extra_state"] = extra_state
|
| 238 |
+
|
| 239 |
+
torch.save(checkpoint, path)
|
| 240 |
+
print(f"✅ Checkpoint sauvegardé: {path}")
|
| 241 |
+
|
| 242 |
+
|
| 243 |
+
def load_cognitive_checkpoint(
|
| 244 |
+
model, path: str, strict: bool = False, verbose: bool = True
|
| 245 |
+
) -> Dict:
|
| 246 |
+
"""
|
| 247 |
+
Charger un checkpoint dans un modèle cognitif avec remappage automatique.
|
| 248 |
+
|
| 249 |
+
Args:
|
| 250 |
+
model: Le modèle cible
|
| 251 |
+
path: Chemin du checkpoint
|
| 252 |
+
strict: Mode strict (erreur si clés manquantes)
|
| 253 |
+
verbose: Afficher les détails
|
| 254 |
+
|
| 255 |
+
Returns:
|
| 256 |
+
Dict avec informations de chargement
|
| 257 |
+
"""
|
| 258 |
+
checkpoint = torch.load(path, map_location="cpu")
|
| 259 |
+
|
| 260 |
+
# Extraire le state_dict
|
| 261 |
+
if "model_state_dict" in checkpoint:
|
| 262 |
+
state_dict = checkpoint["model_state_dict"]
|
| 263 |
+
elif "state_dict" in checkpoint:
|
| 264 |
+
state_dict = checkpoint["state_dict"]
|
| 265 |
+
else:
|
| 266 |
+
state_dict = checkpoint
|
| 267 |
+
|
| 268 |
+
# Remapper les clés
|
| 269 |
+
remapped = remap_checkpoint_keys(state_dict, model.state_dict(), verbose=verbose)
|
| 270 |
+
|
| 271 |
+
# Valider
|
| 272 |
+
validation = validate_checkpoint(remapped, model.state_dict(), strict=strict)
|
| 273 |
+
|
| 274 |
+
if verbose:
|
| 275 |
+
print(
|
| 276 |
+
f"📊 Clés chargées: {validation['matched_keys']}/{validation['total_model_keys']}"
|
| 277 |
+
)
|
| 278 |
+
if validation["missing_keys"]:
|
| 279 |
+
print(f"⚠️ Clés manquantes: {len(validation['missing_keys'])}")
|
| 280 |
+
if validation["size_mismatches"]:
|
| 281 |
+
print(f"⚠️ Tailles incompatibles: {len(validation['size_mismatches'])}")
|
| 282 |
+
|
| 283 |
+
# Charger avec ignore_mismatched_sizes pour robustesse
|
| 284 |
+
model.load_state_dict(remapped, strict=False)
|
| 285 |
+
|
| 286 |
+
# Restaurer l'état cognitif si disponible
|
| 287 |
+
if "cognitive_state" in checkpoint and hasattr(model, "reset_cognitive_state"):
|
| 288 |
+
# L'état cognitif est généralement réinitialisé, pas restauré
|
| 289 |
+
pass
|
| 290 |
+
|
| 291 |
+
if verbose:
|
| 292 |
+
print("✅ Checkpoint chargé avec succès")
|
| 293 |
+
|
| 294 |
+
return {
|
| 295 |
+
"validation": validation,
|
| 296 |
+
"config": checkpoint.get("config", {}),
|
| 297 |
+
"extra_state": checkpoint.get("extra_state", {}),
|
| 298 |
+
}
|
cognitive_training.py
ADDED
|
@@ -0,0 +1,372 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
COGNITIVE-CORE: Training Utilities
|
| 3 |
+
====================================
|
| 4 |
+
|
| 5 |
+
Standardized training utilities for cognitive models, including:
|
| 6 |
+
- Training configurations
|
| 7 |
+
- Trainer wrappers
|
| 8 |
+
- Dataset preparation helpers
|
| 9 |
+
- Progress tracking
|
| 10 |
+
|
| 11 |
+
Copyright © 2026 Mike Amega (Logo) - Ame Web Studio
|
| 12 |
+
License: Proprietary - All Rights Reserved
|
| 13 |
+
"""
|
| 14 |
+
|
| 15 |
+
import os
|
| 16 |
+
import torch
|
| 17 |
+
import torch.nn as nn
|
| 18 |
+
from typing import Dict, List, Optional, Any, Callable
|
| 19 |
+
from dataclasses import dataclass, field
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
# ==============================================================================
|
| 23 |
+
# CONFIGURATION D'ENTRAÎNEMENT
|
| 24 |
+
# ==============================================================================
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
@dataclass
|
| 28 |
+
class CognitiveTrainingConfig:
|
| 29 |
+
"""
|
| 30 |
+
Configuration standard pour l'entraînement de modèles cognitifs.
|
| 31 |
+
"""
|
| 32 |
+
|
| 33 |
+
# Output
|
| 34 |
+
output_dir: str = "./cognitive-output"
|
| 35 |
+
|
| 36 |
+
# Training params
|
| 37 |
+
num_epochs: int = 1
|
| 38 |
+
batch_size: int = 1
|
| 39 |
+
gradient_accumulation_steps: int = 8
|
| 40 |
+
learning_rate: float = 1e-5
|
| 41 |
+
warmup_steps: int = 100
|
| 42 |
+
weight_decay: float = 0.01
|
| 43 |
+
max_grad_norm: float = 1.0
|
| 44 |
+
|
| 45 |
+
# Sequence
|
| 46 |
+
max_seq_len: int = 2048 # IMPORTANT: >= 2048 pour modules cognitifs
|
| 47 |
+
|
| 48 |
+
# Precision
|
| 49 |
+
use_fp16: bool = True
|
| 50 |
+
use_bf16: bool = False
|
| 51 |
+
|
| 52 |
+
# Logging
|
| 53 |
+
logging_steps: int = 10
|
| 54 |
+
save_steps: int = 200
|
| 55 |
+
save_total_limit: int = 2
|
| 56 |
+
|
| 57 |
+
# Hub
|
| 58 |
+
push_to_hub: bool = False
|
| 59 |
+
hub_model_id: Optional[str] = None
|
| 60 |
+
hub_private: bool = True
|
| 61 |
+
|
| 62 |
+
# Device
|
| 63 |
+
device: Optional[str] = None # auto-detected if None
|
| 64 |
+
|
| 65 |
+
def __post_init__(self):
|
| 66 |
+
os.makedirs(self.output_dir, exist_ok=True)
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
# ==============================================================================
|
| 70 |
+
# PRÉPARATION DES DONNÉES
|
| 71 |
+
# ==============================================================================
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
def prepare_dataset(
|
| 75 |
+
dataset,
|
| 76 |
+
tokenizer,
|
| 77 |
+
text_column: str = "text",
|
| 78 |
+
max_length: int = 2048,
|
| 79 |
+
num_proc: int = 4,
|
| 80 |
+
):
|
| 81 |
+
"""
|
| 82 |
+
Prépare un dataset pour l'entraînement d'un modèle cognitif.
|
| 83 |
+
|
| 84 |
+
Args:
|
| 85 |
+
dataset: Dataset HuggingFace
|
| 86 |
+
tokenizer: Tokenizer du modèle
|
| 87 |
+
text_column: Nom de la colonne contenant le texte
|
| 88 |
+
max_length: Longueur maximale des séquences
|
| 89 |
+
num_proc: Nombre de processus pour le mapping
|
| 90 |
+
|
| 91 |
+
Returns:
|
| 92 |
+
Dataset tokenisé prêt pour l'entraînement
|
| 93 |
+
"""
|
| 94 |
+
|
| 95 |
+
def tokenize_function(examples):
|
| 96 |
+
texts = examples[text_column]
|
| 97 |
+
if not isinstance(texts, list):
|
| 98 |
+
texts = [texts]
|
| 99 |
+
|
| 100 |
+
return tokenizer(
|
| 101 |
+
texts,
|
| 102 |
+
truncation=True,
|
| 103 |
+
padding="max_length",
|
| 104 |
+
max_length=max_length,
|
| 105 |
+
return_tensors=None,
|
| 106 |
+
)
|
| 107 |
+
|
| 108 |
+
# Supprimer les colonnes originales
|
| 109 |
+
columns_to_remove = dataset.column_names
|
| 110 |
+
if isinstance(columns_to_remove, dict):
|
| 111 |
+
columns_to_remove = columns_to_remove.get("train", [])
|
| 112 |
+
|
| 113 |
+
tokenized = dataset.map(
|
| 114 |
+
tokenize_function,
|
| 115 |
+
batched=True,
|
| 116 |
+
num_proc=num_proc,
|
| 117 |
+
remove_columns=columns_to_remove,
|
| 118 |
+
)
|
| 119 |
+
|
| 120 |
+
tokenized.set_format(type="torch")
|
| 121 |
+
return tokenized
|
| 122 |
+
|
| 123 |
+
|
| 124 |
+
def create_instruction_dataset(
|
| 125 |
+
examples: List[Dict[str, str]],
|
| 126 |
+
tokenizer,
|
| 127 |
+
max_length: int = 2048,
|
| 128 |
+
instruction_template: str = "### Instruction:\n{instruction}\n\n### Response:\n{response}",
|
| 129 |
+
):
|
| 130 |
+
"""
|
| 131 |
+
Crée un dataset d'instructions à partir d'exemples.
|
| 132 |
+
|
| 133 |
+
Args:
|
| 134 |
+
examples: Liste de dicts avec 'instruction' et 'response'
|
| 135 |
+
tokenizer: Tokenizer du modèle
|
| 136 |
+
max_length: Longueur maximale
|
| 137 |
+
instruction_template: Template de formatage
|
| 138 |
+
|
| 139 |
+
Returns:
|
| 140 |
+
Dataset tokenisé
|
| 141 |
+
"""
|
| 142 |
+
from datasets import Dataset
|
| 143 |
+
|
| 144 |
+
formatted = []
|
| 145 |
+
for ex in examples:
|
| 146 |
+
text = instruction_template.format(
|
| 147 |
+
instruction=ex.get("instruction", ""), response=ex.get("response", "")
|
| 148 |
+
)
|
| 149 |
+
formatted.append({"text": text})
|
| 150 |
+
|
| 151 |
+
dataset = Dataset.from_list(formatted)
|
| 152 |
+
return prepare_dataset(dataset, tokenizer, "text", max_length)
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
# ==============================================================================
|
| 156 |
+
# TRAINER WRAPPER
|
| 157 |
+
# ==============================================================================
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
class CognitiveTrainer:
|
| 161 |
+
"""
|
| 162 |
+
Trainer simplifié pour modèles cognitifs.
|
| 163 |
+
|
| 164 |
+
Wrapper autour du Trainer HuggingFace avec configuration optimisée
|
| 165 |
+
pour les architectures cognitives.
|
| 166 |
+
"""
|
| 167 |
+
|
| 168 |
+
def __init__(
|
| 169 |
+
self,
|
| 170 |
+
model,
|
| 171 |
+
tokenizer,
|
| 172 |
+
train_dataset,
|
| 173 |
+
config: CognitiveTrainingConfig,
|
| 174 |
+
eval_dataset=None,
|
| 175 |
+
callbacks: Optional[List] = None,
|
| 176 |
+
):
|
| 177 |
+
self.model = model
|
| 178 |
+
self.tokenizer = tokenizer
|
| 179 |
+
self.train_dataset = train_dataset
|
| 180 |
+
self.eval_dataset = eval_dataset
|
| 181 |
+
self.config = config
|
| 182 |
+
self.callbacks = callbacks or []
|
| 183 |
+
|
| 184 |
+
# Configurer tokenizer
|
| 185 |
+
if tokenizer.pad_token is None:
|
| 186 |
+
tokenizer.pad_token = tokenizer.eos_token
|
| 187 |
+
|
| 188 |
+
self._setup_trainer()
|
| 189 |
+
|
| 190 |
+
def _setup_trainer(self):
|
| 191 |
+
"""Configure le Trainer HuggingFace."""
|
| 192 |
+
from transformers import (
|
| 193 |
+
Trainer,
|
| 194 |
+
TrainingArguments,
|
| 195 |
+
DataCollatorForLanguageModeling,
|
| 196 |
+
)
|
| 197 |
+
|
| 198 |
+
# Déterminer device
|
| 199 |
+
if self.config.device:
|
| 200 |
+
device = self.config.device
|
| 201 |
+
elif torch.cuda.is_available():
|
| 202 |
+
device = "cuda"
|
| 203 |
+
else:
|
| 204 |
+
device = "cpu"
|
| 205 |
+
|
| 206 |
+
# Arguments d'entraînement
|
| 207 |
+
training_args = TrainingArguments(
|
| 208 |
+
output_dir=self.config.output_dir,
|
| 209 |
+
overwrite_output_dir=True,
|
| 210 |
+
num_train_epochs=self.config.num_epochs,
|
| 211 |
+
per_device_train_batch_size=self.config.batch_size,
|
| 212 |
+
gradient_accumulation_steps=self.config.gradient_accumulation_steps,
|
| 213 |
+
learning_rate=self.config.learning_rate,
|
| 214 |
+
warmup_steps=self.config.warmup_steps,
|
| 215 |
+
weight_decay=self.config.weight_decay,
|
| 216 |
+
max_grad_norm=self.config.max_grad_norm,
|
| 217 |
+
logging_steps=self.config.logging_steps,
|
| 218 |
+
save_steps=self.config.save_steps,
|
| 219 |
+
save_total_limit=self.config.save_total_limit,
|
| 220 |
+
fp16=self.config.use_fp16 and device == "cuda",
|
| 221 |
+
bf16=self.config.use_bf16 and device == "cuda",
|
| 222 |
+
push_to_hub=self.config.push_to_hub,
|
| 223 |
+
hub_model_id=self.config.hub_model_id,
|
| 224 |
+
hub_private_repo=self.config.hub_private,
|
| 225 |
+
report_to="none",
|
| 226 |
+
remove_unused_columns=False,
|
| 227 |
+
dataloader_num_workers=0, # Évite problèmes sur certains environnements
|
| 228 |
+
)
|
| 229 |
+
|
| 230 |
+
# Data collator
|
| 231 |
+
data_collator = DataCollatorForLanguageModeling(
|
| 232 |
+
tokenizer=self.tokenizer, mlm=False
|
| 233 |
+
)
|
| 234 |
+
|
| 235 |
+
# Créer le trainer
|
| 236 |
+
self.trainer = Trainer(
|
| 237 |
+
model=self.model,
|
| 238 |
+
args=training_args,
|
| 239 |
+
train_dataset=self.train_dataset,
|
| 240 |
+
eval_dataset=self.eval_dataset,
|
| 241 |
+
data_collator=data_collator,
|
| 242 |
+
tokenizer=self.tokenizer,
|
| 243 |
+
callbacks=self.callbacks,
|
| 244 |
+
)
|
| 245 |
+
|
| 246 |
+
def train(self, resume_from_checkpoint: Optional[str] = None):
|
| 247 |
+
"""
|
| 248 |
+
Lance l'entraînement.
|
| 249 |
+
|
| 250 |
+
Args:
|
| 251 |
+
resume_from_checkpoint: Chemin pour reprendre l'entraînement
|
| 252 |
+
|
| 253 |
+
Returns:
|
| 254 |
+
Résultats de l'entraînement
|
| 255 |
+
"""
|
| 256 |
+
print("\n🚀 ENTRAÎNEMENT COGNITIF")
|
| 257 |
+
print("=" * 60)
|
| 258 |
+
|
| 259 |
+
try:
|
| 260 |
+
result = self.trainer.train(resume_from_checkpoint=resume_from_checkpoint)
|
| 261 |
+
print("=" * 60)
|
| 262 |
+
print("✅ Entraînement terminé!")
|
| 263 |
+
return result
|
| 264 |
+
except Exception as e:
|
| 265 |
+
print(f"❌ Erreur: {e}")
|
| 266 |
+
import traceback
|
| 267 |
+
|
| 268 |
+
traceback.print_exc()
|
| 269 |
+
return None
|
| 270 |
+
|
| 271 |
+
def save(self, output_dir: Optional[str] = None):
|
| 272 |
+
"""Sauvegarde le modèle et tokenizer."""
|
| 273 |
+
save_dir = output_dir or self.config.output_dir
|
| 274 |
+
self.trainer.save_model(save_dir)
|
| 275 |
+
self.tokenizer.save_pretrained(save_dir)
|
| 276 |
+
print(f"💾 Modèle sauvegardé: {save_dir}")
|
| 277 |
+
|
| 278 |
+
def push_to_hub(self, repo_id: Optional[str] = None):
|
| 279 |
+
"""Push le modèle vers HuggingFace Hub."""
|
| 280 |
+
if repo_id:
|
| 281 |
+
self.config.hub_model_id = repo_id
|
| 282 |
+
|
| 283 |
+
try:
|
| 284 |
+
self.trainer.push_to_hub()
|
| 285 |
+
print(f"📤 Modèle pushé: {self.config.hub_model_id}")
|
| 286 |
+
except Exception as e:
|
| 287 |
+
print(f"⚠️ Erreur push: {e}")
|
| 288 |
+
|
| 289 |
+
|
| 290 |
+
# ==============================================================================
|
| 291 |
+
# CALLBACKS PERSONNALISÉS
|
| 292 |
+
# ==============================================================================
|
| 293 |
+
|
| 294 |
+
|
| 295 |
+
class CognitiveStateCallback:
|
| 296 |
+
"""
|
| 297 |
+
Callback pour monitorer l'état des modules cognitifs pendant l'entraînement.
|
| 298 |
+
"""
|
| 299 |
+
|
| 300 |
+
def __init__(self, log_every: int = 100):
|
| 301 |
+
self.log_every = log_every
|
| 302 |
+
self.step = 0
|
| 303 |
+
|
| 304 |
+
def on_step_end(self, args, state, control, model=None, **kwargs):
|
| 305 |
+
self.step += 1
|
| 306 |
+
|
| 307 |
+
if self.step % self.log_every == 0 and model is not None:
|
| 308 |
+
if hasattr(model, "get_cognitive_state"):
|
| 309 |
+
cog_state = model.get_cognitive_state()
|
| 310 |
+
print(f"\n📊 État cognitif (step {self.step}):")
|
| 311 |
+
for name, state_dict in cog_state.items():
|
| 312 |
+
if state_dict:
|
| 313 |
+
print(f" {name}: {len(state_dict)} buffers")
|
| 314 |
+
|
| 315 |
+
|
| 316 |
+
# ==============================================================================
|
| 317 |
+
# QUICK TRAIN FUNCTION
|
| 318 |
+
# ==============================================================================
|
| 319 |
+
|
| 320 |
+
|
| 321 |
+
def quick_train(
|
| 322 |
+
model,
|
| 323 |
+
tokenizer,
|
| 324 |
+
texts: List[str],
|
| 325 |
+
output_dir: str = "./quick-train-output",
|
| 326 |
+
num_epochs: int = 1,
|
| 327 |
+
max_seq_len: int = 2048,
|
| 328 |
+
learning_rate: float = 1e-5,
|
| 329 |
+
push_to_hub: bool = False,
|
| 330 |
+
hub_model_id: Optional[str] = None,
|
| 331 |
+
):
|
| 332 |
+
"""
|
| 333 |
+
Entraînement rapide avec configuration minimale.
|
| 334 |
+
|
| 335 |
+
Args:
|
| 336 |
+
model: Modèle à entraîner
|
| 337 |
+
tokenizer: Tokenizer
|
| 338 |
+
texts: Liste de textes d'entraînement
|
| 339 |
+
output_dir: Répertoire de sortie
|
| 340 |
+
num_epochs: Nombre d'époques
|
| 341 |
+
max_seq_len: Longueur max des séquences
|
| 342 |
+
learning_rate: Taux d'apprentissage
|
| 343 |
+
push_to_hub: Pusher vers HuggingFace
|
| 344 |
+
hub_model_id: ID du repo HuggingFace
|
| 345 |
+
|
| 346 |
+
Returns:
|
| 347 |
+
Résultats de l'entraînement
|
| 348 |
+
"""
|
| 349 |
+
from datasets import Dataset
|
| 350 |
+
|
| 351 |
+
# Créer dataset
|
| 352 |
+
dataset = Dataset.from_dict({"text": texts})
|
| 353 |
+
tokenized = prepare_dataset(dataset, tokenizer, "text", max_seq_len)
|
| 354 |
+
|
| 355 |
+
# Config
|
| 356 |
+
config = CognitiveTrainingConfig(
|
| 357 |
+
output_dir=output_dir,
|
| 358 |
+
num_epochs=num_epochs,
|
| 359 |
+
max_seq_len=max_seq_len,
|
| 360 |
+
learning_rate=learning_rate,
|
| 361 |
+
push_to_hub=push_to_hub,
|
| 362 |
+
hub_model_id=hub_model_id,
|
| 363 |
+
)
|
| 364 |
+
|
| 365 |
+
# Trainer
|
| 366 |
+
trainer = CognitiveTrainer(model, tokenizer, tokenized, config)
|
| 367 |
+
result = trainer.train()
|
| 368 |
+
|
| 369 |
+
if result:
|
| 370 |
+
trainer.save()
|
| 371 |
+
|
| 372 |
+
return result
|
cognitive_utils.py
ADDED
|
@@ -0,0 +1,282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
COGNITIVE-CORE: Utility Functions
|
| 3 |
+
==================================
|
| 4 |
+
|
| 5 |
+
Common utilities for cognitive model development, including:
|
| 6 |
+
- Environment setup for Kaggle/Colab
|
| 7 |
+
- Device detection
|
| 8 |
+
- Memory optimization helpers
|
| 9 |
+
- Logging utilities
|
| 10 |
+
|
| 11 |
+
Copyright © 2026 Mike Amega (Logo) - Ame Web Studio
|
| 12 |
+
License: Proprietary - All Rights Reserved
|
| 13 |
+
"""
|
| 14 |
+
|
| 15 |
+
import os
|
| 16 |
+
import sys
|
| 17 |
+
import torch
|
| 18 |
+
import warnings
|
| 19 |
+
from typing import Optional, Dict, Any
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
# ==============================================================================
|
| 23 |
+
# ENVIRONNEMENT & CACHE
|
| 24 |
+
# ==============================================================================
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
def setup_environment(cache_dir: Optional[str] = None) -> str:
|
| 28 |
+
"""
|
| 29 |
+
Configure l'environnement pour Kaggle/Colab/Local.
|
| 30 |
+
|
| 31 |
+
Résout les problèmes de:
|
| 32 |
+
- Read-only file system sur Kaggle
|
| 33 |
+
- Chemins de cache HuggingFace
|
| 34 |
+
|
| 35 |
+
Args:
|
| 36 |
+
cache_dir: Répertoire cache personnalisé (optionnel)
|
| 37 |
+
|
| 38 |
+
Returns:
|
| 39 |
+
Chemin du répertoire cache configuré
|
| 40 |
+
"""
|
| 41 |
+
if cache_dir is None:
|
| 42 |
+
# Détecter l'environnement
|
| 43 |
+
if os.path.exists("/kaggle"):
|
| 44 |
+
cache_dir = "/kaggle/working/.cache"
|
| 45 |
+
elif os.path.exists("/content"): # Colab
|
| 46 |
+
cache_dir = "/content/.cache"
|
| 47 |
+
else:
|
| 48 |
+
cache_dir = os.path.expanduser("~/.cache/cognitive")
|
| 49 |
+
|
| 50 |
+
# Créer le répertoire
|
| 51 |
+
os.makedirs(cache_dir, exist_ok=True)
|
| 52 |
+
os.makedirs(os.path.join(cache_dir, "datasets"), exist_ok=True)
|
| 53 |
+
|
| 54 |
+
# Configurer les variables d'environnement
|
| 55 |
+
os.environ["HF_HOME"] = cache_dir
|
| 56 |
+
os.environ["TRANSFORMERS_CACHE"] = cache_dir
|
| 57 |
+
os.environ["HF_DATASETS_CACHE"] = os.path.join(cache_dir, "datasets")
|
| 58 |
+
|
| 59 |
+
# Désactiver les warnings non critiques
|
| 60 |
+
warnings.filterwarnings("ignore", category=FutureWarning)
|
| 61 |
+
warnings.filterwarnings("ignore", category=UserWarning, module="transformers")
|
| 62 |
+
|
| 63 |
+
return cache_dir
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
def get_device(prefer_gpu: bool = True) -> torch.device:
|
| 67 |
+
"""
|
| 68 |
+
Détecte et retourne le meilleur device disponible.
|
| 69 |
+
|
| 70 |
+
Args:
|
| 71 |
+
prefer_gpu: Préférer GPU si disponible
|
| 72 |
+
|
| 73 |
+
Returns:
|
| 74 |
+
torch.device configuré
|
| 75 |
+
"""
|
| 76 |
+
if prefer_gpu and torch.cuda.is_available():
|
| 77 |
+
device = torch.device("cuda")
|
| 78 |
+
gpu_name = torch.cuda.get_device_name(0)
|
| 79 |
+
gpu_mem = torch.cuda.get_device_properties(0).total_memory / 1e9
|
| 80 |
+
print(f"🔧 GPU: {gpu_name} ({gpu_mem:.1f} GB)")
|
| 81 |
+
elif (
|
| 82 |
+
prefer_gpu
|
| 83 |
+
and hasattr(torch.backends, "mps")
|
| 84 |
+
and torch.backends.mps.is_available()
|
| 85 |
+
):
|
| 86 |
+
device = torch.device("mps")
|
| 87 |
+
print("🔧 Apple MPS")
|
| 88 |
+
else:
|
| 89 |
+
device = torch.device("cpu")
|
| 90 |
+
print("🔧 CPU")
|
| 91 |
+
|
| 92 |
+
return device
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def get_optimal_dtype(device: torch.device) -> torch.dtype:
|
| 96 |
+
"""
|
| 97 |
+
Retourne le dtype optimal pour le device.
|
| 98 |
+
|
| 99 |
+
Args:
|
| 100 |
+
device: Le device cible
|
| 101 |
+
|
| 102 |
+
Returns:
|
| 103 |
+
torch.dtype optimal (float16 pour GPU, float32 pour CPU)
|
| 104 |
+
"""
|
| 105 |
+
if device.type == "cuda":
|
| 106 |
+
# Vérifier support BF16
|
| 107 |
+
if torch.cuda.is_bf16_supported():
|
| 108 |
+
return torch.bfloat16
|
| 109 |
+
return torch.float16
|
| 110 |
+
return torch.float32
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
# ==============================================================================
|
| 114 |
+
# MÉMOIRE & OPTIMISATION
|
| 115 |
+
# ==============================================================================
|
| 116 |
+
|
| 117 |
+
|
| 118 |
+
def get_memory_info() -> Dict[str, float]:
|
| 119 |
+
"""
|
| 120 |
+
Retourne les informations mémoire (GPU si disponible).
|
| 121 |
+
|
| 122 |
+
Returns:
|
| 123 |
+
Dict avec allocated, reserved, free en GB
|
| 124 |
+
"""
|
| 125 |
+
if torch.cuda.is_available():
|
| 126 |
+
allocated = torch.cuda.memory_allocated() / 1e9
|
| 127 |
+
reserved = torch.cuda.memory_reserved() / 1e9
|
| 128 |
+
total = torch.cuda.get_device_properties(0).total_memory / 1e9
|
| 129 |
+
return {
|
| 130 |
+
"allocated_gb": allocated,
|
| 131 |
+
"reserved_gb": reserved,
|
| 132 |
+
"free_gb": total - allocated,
|
| 133 |
+
"total_gb": total,
|
| 134 |
+
}
|
| 135 |
+
return {"allocated_gb": 0, "reserved_gb": 0, "free_gb": 0, "total_gb": 0}
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
def clear_memory():
|
| 139 |
+
"""Libère la mémoire GPU si possible."""
|
| 140 |
+
if torch.cuda.is_available():
|
| 141 |
+
torch.cuda.empty_cache()
|
| 142 |
+
torch.cuda.synchronize()
|
| 143 |
+
|
| 144 |
+
|
| 145 |
+
def estimate_model_memory(model, dtype: torch.dtype = torch.float32) -> float:
|
| 146 |
+
"""
|
| 147 |
+
Estime la mémoire nécessaire pour un modèle.
|
| 148 |
+
|
| 149 |
+
Args:
|
| 150 |
+
model: Le modèle PyTorch
|
| 151 |
+
dtype: Le dtype utilisé
|
| 152 |
+
|
| 153 |
+
Returns:
|
| 154 |
+
Estimation en GB
|
| 155 |
+
"""
|
| 156 |
+
param_bytes = sum(p.numel() * p.element_size() for p in model.parameters())
|
| 157 |
+
buffer_bytes = sum(b.numel() * b.element_size() for b in model.buffers())
|
| 158 |
+
|
| 159 |
+
# Facteur pour activations (estimation: 2x les paramètres)
|
| 160 |
+
activation_factor = 2.0
|
| 161 |
+
|
| 162 |
+
total_bytes = (param_bytes + buffer_bytes) * activation_factor
|
| 163 |
+
|
| 164 |
+
# Ajuster selon dtype
|
| 165 |
+
if dtype in (torch.float16, torch.bfloat16):
|
| 166 |
+
total_bytes *= 0.5
|
| 167 |
+
|
| 168 |
+
return total_bytes / 1e9
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
# ==============================================================================
|
| 172 |
+
# LOGGING & AFFICHAGE
|
| 173 |
+
# ==============================================================================
|
| 174 |
+
|
| 175 |
+
|
| 176 |
+
def print_model_info(model, show_params: bool = True):
|
| 177 |
+
"""
|
| 178 |
+
Affiche les informations du modèle.
|
| 179 |
+
|
| 180 |
+
Args:
|
| 181 |
+
model: Le modèle à analyser
|
| 182 |
+
show_params: Afficher le détail des paramètres
|
| 183 |
+
"""
|
| 184 |
+
total_params = sum(p.numel() for p in model.parameters())
|
| 185 |
+
trainable_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
|
| 186 |
+
|
| 187 |
+
print(f"\n📊 MODÈLE: {model.__class__.__name__}")
|
| 188 |
+
print(f" Total paramètres: {total_params:,}")
|
| 189 |
+
print(f" Paramètres entraînables: {trainable_params:,}")
|
| 190 |
+
print(f" Mémoire estimée: {estimate_model_memory(model):.2f} GB")
|
| 191 |
+
|
| 192 |
+
if show_params and hasattr(model, "config"):
|
| 193 |
+
print(f"\n Configuration:")
|
| 194 |
+
for key in ["d_model", "n_layers", "n_heads", "vocab_size"]:
|
| 195 |
+
if hasattr(model.config, key):
|
| 196 |
+
print(f" - {key}: {getattr(model.config, key)}")
|
| 197 |
+
|
| 198 |
+
|
| 199 |
+
def print_training_progress(
|
| 200 |
+
step: int,
|
| 201 |
+
total_steps: int,
|
| 202 |
+
loss: float,
|
| 203 |
+
lr: Optional[float] = None,
|
| 204 |
+
extras: Optional[Dict[str, float]] = None,
|
| 205 |
+
):
|
| 206 |
+
"""
|
| 207 |
+
Affiche la progression d'entraînement.
|
| 208 |
+
|
| 209 |
+
Args:
|
| 210 |
+
step: Étape actuelle
|
| 211 |
+
total_steps: Nombre total d'étapes
|
| 212 |
+
loss: Valeur de la loss
|
| 213 |
+
lr: Learning rate actuel
|
| 214 |
+
extras: Métriques additionnelles
|
| 215 |
+
"""
|
| 216 |
+
progress = step / total_steps * 100
|
| 217 |
+
msg = f"[{step:>6}/{total_steps}] ({progress:>5.1f}%) | Loss: {loss:.4f}"
|
| 218 |
+
|
| 219 |
+
if lr is not None:
|
| 220 |
+
msg += f" | LR: {lr:.2e}"
|
| 221 |
+
|
| 222 |
+
if extras:
|
| 223 |
+
for key, val in extras.items():
|
| 224 |
+
msg += f" | {key}: {val:.4f}"
|
| 225 |
+
|
| 226 |
+
print(msg)
|
| 227 |
+
|
| 228 |
+
|
| 229 |
+
# ==============================================================================
|
| 230 |
+
# TOKEN HUGGINGFACE
|
| 231 |
+
# ==============================================================================
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
def get_hf_token() -> Optional[str]:
|
| 235 |
+
"""
|
| 236 |
+
Récupère le token HuggingFace depuis différentes sources.
|
| 237 |
+
|
| 238 |
+
Ordre de recherche:
|
| 239 |
+
1. Variable d'environnement HF_TOKEN
|
| 240 |
+
2. Secrets Kaggle
|
| 241 |
+
3. Secrets Colab
|
| 242 |
+
4. Token local HuggingFace CLI
|
| 243 |
+
|
| 244 |
+
Returns:
|
| 245 |
+
Token ou None si non trouvé
|
| 246 |
+
"""
|
| 247 |
+
# Env var
|
| 248 |
+
token = os.environ.get("HF_TOKEN")
|
| 249 |
+
if token:
|
| 250 |
+
return token
|
| 251 |
+
|
| 252 |
+
# Kaggle
|
| 253 |
+
try:
|
| 254 |
+
from kaggle_secrets import UserSecretsClient
|
| 255 |
+
|
| 256 |
+
token = UserSecretsClient().get_secret("HF_TOKEN")
|
| 257 |
+
if token:
|
| 258 |
+
return token
|
| 259 |
+
except Exception:
|
| 260 |
+
pass
|
| 261 |
+
|
| 262 |
+
# Colab
|
| 263 |
+
try:
|
| 264 |
+
from google.colab import userdata
|
| 265 |
+
|
| 266 |
+
token = userdata.get("HF_TOKEN")
|
| 267 |
+
if token:
|
| 268 |
+
return token
|
| 269 |
+
except Exception:
|
| 270 |
+
pass
|
| 271 |
+
|
| 272 |
+
# Local HuggingFace CLI
|
| 273 |
+
try:
|
| 274 |
+
from huggingface_hub import HfFolder
|
| 275 |
+
|
| 276 |
+
token = HfFolder.get_token()
|
| 277 |
+
if token:
|
| 278 |
+
return token
|
| 279 |
+
except Exception:
|
| 280 |
+
pass
|
| 281 |
+
|
| 282 |
+
return None
|