← All Models | GPT - OpenAI's Generative Pre-trained Transformers:

openai-community/gpt2

📊 Model Parameters

Total Parameters 163,037,184
Context Length 1,024
Hidden Size 768
Layers 12
Attention Heads 12
KV Heads 12

💾 Memory Requirements

FP32 (Full) 621.9 MB
FP16 (Half) 311.0 MB
INT8 (Quantized) 155.5 MB
INT4 (Quantized) 77.7 MB

🔑 KV Cache (Inference)

Per Token (FP16) 36.86 KB
Max Context FP32 72.0 MB
Max Context FP16 36.0 MB
Max Context INT8 18.0 MB

⚙️ Model Configuration

Core Architecture

Vocabulary Size50,257
Number of Layers12
Attention Heads12
FFN Intermediate SizeNot set

Context & Position

Max Context Length1,024

Attention Configuration

Attention Dropout10.0%
Tied EmbeddingsYes

Activation & Normalization

Activation Functiongelu_new
RMSNorm Epsilon1e-05

Dropout (Training)

Residual Dropout10.0%
Embedding Dropout10.0%

Special Tokens

BOS Token ID50,256
EOS Token ID50256
Pad Token IDNot set

Data Type

Model DtypeNot set
Layer Types:
Attention
MLP/FFN
Normalization
Embedding