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

openai-community/gpt2-large

📊 Model Parameters

Total Parameters 838,359,040
Context Length 1,024
Hidden Size 1280
Layers 36
Attention Heads 20
KV Heads 20

💾 Memory Requirements

FP32 (Full) 3.12 GB
FP16 (Half) 1.56 GB
INT8 (Quantized) 799.5 MB
INT4 (Quantized) 399.8 MB

🔑 KV Cache (Inference)

Per Token (FP16) 184.32 KB
Max Context FP32 360.0 MB
Max Context FP16 180.0 MB
Max Context INT8 90.0 MB

⚙️ Model Configuration

Core Architecture

Vocabulary Size50,257
Number of Layers36
Attention Heads20
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