flowchart TD
A[Tech Tree] --> B[Python]
%% --- Dataset ---
subgraph DS[Dataset]
C[Basic Dataset] --> R[Data Collection]
R --> S[Data Cleaning]
S --> T[Tokenisation]
T --> U[Byte Pair Encoding]
U --> V[Causal Language Modelling]
V --> W[Positional Encoding]
W --> X[Rotary Positional Encoding]
end
%% --- Operaciones Básicas ---
subgraph OP[Operaciones Básicas]
D[Tensor]
E[Basic Operations]
Y[Linear Layer]
Z[ReLU]
AA[Swish]
AB[GeLU]
AC[SiLU/Swish]
AD[Attention]
AE[Multi-Head Attention]
end
%% --- Entrenamiento ---
subgraph TR[Entrenamiento]
F[Autograd]
G[Mean Squared Error]
H[Cross Entropy]
I[Backpropagation]
J[Stochastic Gradient Descent]
K[Weight Decay]
L[Momentum]
M[Learning rate]
N[Gradient Clipping]
O[AdamW]
AN[Hyperparameter Tuning]
AO[μ-Scaling Laws]
end
%% --- Arquitectura ---
subgraph ARQ[Arquitectura]
AF[Multi-Layer Perceptron]
Q[Transformer Block]
AG[Transformer]
AH[Small Language Model]
AI[Modern Language Model]
AJ[Quantisation]
AK[Batch Norm]
AL[Layer Norm]
AM[RMSNorm]
end
%% Relaciones principales
B --> C
B --> D
B --> E
D --> F
F --> G
F --> H
F --> I
I --> J
J --> K
J --> L
J --> M
J --> N
J --> O
O --> Q
E --> Y
Y --> Z
Y --> AA
Y --> AB
AA --> AC
Y --> AD
AD --> AE
Z --> AF
AA --> AF
AB --> AF
AC --> AF
AF --> Q
AE --> Q
I --> Y
Q --> AG
AG --> AH
AH --> AI
AI --> AJ
AH --> AK
AH --> AL
AH --> AM
K --> Q
L --> Q
M --> Q
N --> Q
AN --> AO --> Q
