Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense f…

Automating the Search for Artificial Life with Foundation Models!

A library for making RepE control vectors

Go ahead and axolotl questions

Notebooks for fine tuning pali gemma

Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.

Dive into the uncharted waters of Maraxsis, a world where the sea covers everything. Utilize submarines to explore, craft advanced fluids inside the hydro plant, build pressure domes, and master th…

Classificador de poemas do Fernando Pessoa de acordo com os seus heterônimos

Gerador de texto treinado nas obras de João Guimarães Rosa

llm sampler that only allows words that are in the bible

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 150+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Inter…

Janus-Series: Unified Multimodal Understanding and Generation Models

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Deep gauge (using Tensorflow to read gauges)

Code repository for "It's About Time: Analog clock Reading in the Wild"

ASCII Playground

Empower lerobot with multimodal Llama 3.2!

Official Implementation for our NeurIPS 2024 paper, "Don't Look Twice: Run-Length Tokenization for Faster Video Transformers".

YOLOv10 trained on DocLayNet dataset.

Code and data to evaluate LLMs on the ENEM, the main standardized Brazilian university admission exams.

i will automate factorio

Bridges a Discord channel an the in game chat in Clusterio

internet communication for factorio mods