babyLM WhisBERT code

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Implementation of the RWKV language model in pure WebGPU/Rust.

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Fine-Tuning of a multi-language transformer model on Nvidia GPUs.

Implements VAR+CLIP for image generation

Run Gemini Nano locally on chrome

Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish

EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction

A Framework of Small-scale Large Multimodal Models

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

A base64 encoder/decoder with gzip or deflate abilities.

Vision-language conversation in 10 languages including English, Chinese, French, Spanish, Russian, Japanese, Arabic, Hindi, Bengali and Urdu.

MobiLlama : Small Language Model tailored for edge devices

this plugin embeds an video player. when upload a video this does not appear as a link but as players in the content. Accepted video formats MP4, WEBM, MOV, OGV。

Lumina-T2X is a unified framework for Text to Any Modality Generation

Examples of Pages using WebM files with Encrypted Media Extensions

A simple MP3 and AAC Decoder (not only) for Arduino based on libhelix

A video player on the M5Stack Core2.

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

ESP32 library that generates composite video signal for PAL, SECAM and NTSC.

Build android apps without any java, entirely in C and Make

Combining ViT and GPT-2 for image captioning. Trained on MS-COCO. The model was implemented mostly from scratch.

GPT in TensorFlow.js

tiny vision language model