OurBigBook
About
$
Donate
Sign in
Sign up
List of GPT models
Ciro Santilli
(
@cirosantilli,
37
)
...
Generative AI by modality
AI text generation
Text-to-text model
Large language model
Generative pre-trained transformer
GPT model
2025-08-08
0
Like
0 By others
on same topic
0 Discussions
Create my own version
Table of contents
GPT model by OpenAI
List of GPT models
GPT-1
GPT model by OpenAI
Improving Language Understanding by Generative Pre-Training
GPT-1
GPT-2
GPT model by OpenAI
Language Models are Unsupervised Multitask Learners
GPT-2
GPT-2 implementation
GPT-2
GPT-2 implementation in PyTorch
GPT-2
nanoGPT
GPT-2 implementation in PyTorch
GPT-2 variant
GPT-2
GPT-2 medium
GPT-2 variant
GPT-2 large
GPT-2 variant
GPT-2 XL
GPT-2 variant
GPT-3
GPT model by OpenAI
GPT-4
GPT model by OpenAI
GPT 4 Turbo
GPT-4
Llama (language model)
List of GPT models
Llama 2
Llama (language model)
Llama 2 7B
Llama 2
Llama 3
Llama (language model)
Llama 3.1
Llama 3
Llama 3.1 8B
Llama 3.1
Llama 3.1 70B
Llama 3.1
Llama 3.1 405B
Llama 3.1
GPT model by OpenAI
0
0
0
List of GPT models
GPT-1
(117 M parameters, 2019-06)
0
0
0
GPT model by OpenAI
Improving Language Understanding by Generative Pre-Training
(GPT-1 paper)
0
0
0
GPT-1
GPT-2
(124 M parameters, 2019-11-05)
0
0
0
GPT model by OpenAI
Vocabulary
size
(
V)
: 50,257
Hidden
size
(
d
_
model)
: 768
Context
length
(
n
_ctx): 1024
Q
V
size
: (
d
_head): 64
Attention heads (
h)
: 12
FFN inner
size
(
d
_ff): 3072
Layers (
L)
: 12
Language Models are Unsupervised Multitask Learners
(GPT-2 paper)
0
0
0
GPT-2
cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
GPT-2 implementation
0
0
0
GPT-2
GPT-2 implementation in PyTorch
0
0
0
GPT-2
Tags:
PyTorch model
nanoGPT
0
0
0
GPT-2 implementation in PyTorch
github.com/karpathy/nanoGPT
GPT-2 variant
0
0
0
GPT-2
GPT-2 medium
(355 M parameters)
0
0
0
GPT-2 variant
GPT-2 large
(774 M parameters)
0
0
0
GPT-2 variant
GPT-2 XL
0
0
0
GPT-2 variant
GPT-3
(175 B parameters, 2020-06)
0
0
0
GPT model by OpenAI
Vocabulary
size
(
V)
: 50,257
Hidden
size
(
d
_
model)
: 12,288
Context
length
2048
Q
V
size
: (
d
_head): 128
Attention heads (
h)
: 96
FFN inner
size
(
d
_ff)
4
× 12,288 = 49,152
Layers (
L)
: 96
GPT-4
0
0
0
GPT model by OpenAI
GPT 4 Turbo
0
0
0
GPT-4
platform.openai.com/docs/models/gpt-4-turbo
Llama
(language model)
0
0
0
List of GPT models
Tags:
Open weight LLM model
,
Software developed by Facebook
Homepage:
www.llama.com/
Llama 2
(2023)
0
0
0
Llama (language model)
Page:
www.llama.com/llama2/
Llama 2 7B
0
0
0
Llama 2
Llama 3
(2024)
0
0
0
Llama (language model)
www.llama.com/models/llama-3/
Llama 3.1
0
0
0
Llama 3
Llama 3.1 8B
0
0
0
Llama 3.1
Llama 3.1 70B
0
0
0
Llama 3.1
Llama 3.1 405B
0
0
0
Llama 3.1
Ancestors
(15)
GPT model
Generative pre-trained transformer
Large language model
Text-to-text model
AI text generation
Generative AI by modality
Generative AI
AI by capability
Artificial intelligence
Machine learning
Computer
Information technology
Area of technology
Technology
Home
View article source
Discussion
(0)
Subscribe (1)
New discussion
There are no discussions about this article yet.
Articles by others on the same topic
(0)
There are currently no matching articles.
See all articles in the same topic
Create my own version