discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
FoundationVision/VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
History and source changes · Reports and owner responses · Compare
Similar
- NielsRogge/Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
Why this match
topics gpt-2, transformers, vision-transformer
- EleutherAI/gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
Why this match
topics gpt, gpt-2, transformers; language differs: Jupyter Notebook → Python
- NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
Why this match
topics large-language-models, transformers; language differs: Jupyter Notebook → Python
- 01-ai/Yi
A series of large language models trained from scratch by developers @01-ai
Why this match
topics large-language-models; license differs: MIT → Apache-2.0
- diff-usion/Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
Why this match
topics diffusion-models, generative-model; language differs: Jupyter Notebook → HTML
- rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Why this match
topics generative-ai, gpt, large-language-models
- FareedKhan-dev/train-llm-from-scratch
A straightforward method for training your LLM, from downloading data to generating text.
Why this match
topics large-language-models, transformers; language differs: Jupyter Notebook → Python
- BlinkDL/RWKV-LM
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
Why this match
topics gpt, gpt-2, transformers; language differs: Jupyter Notebook → Python; license differs: MIT → Apache-2.0