You can now use the highly-scalable #MLFlow AI Gateway for your RAG apps! This blog shows it all in action with a RAG application built using the API gateway, Llama2 and hosted models on MosaicML. Give it a read https://
bit.ly/3OTWA06
OPEN SOURCE
-
MLFlow AI Gateway Now Powers RAG Applications with Llama2
By
–
-
Community Thanks for Contributing Cool LoRA Models
By
–
Thanks for contributing so many cool LoRAs , obrigado!
-
Philippe’s Trolling Reshape Function Naming Convention
By
–
looks like phillippe wanted to troll everyone by calling what should've been `tl.reshape` as `tl.view`.
It's like those trolly C macros ( #define float int ) -
BART Abstractive Text Summarization with KerasNLP and Keras Core
By
–
Abstractive text summarization with BART — using KerasNLP and Keras Core, with JAX
-
Arabic-English-Code Model Enables Multilingual Transfer Learning
By
–
(2/2) Training on an Arabic-English-Code dataset has allowed for transfer learning from English to Arabic and also from Arabic to English. Access the model on Hugging Face: https://
huggingface.co/inception-mbzu
ai
… -
Jais Arabic LLM Outperforms LLaMa 13B Efficiently
By
–
(1/2) Jais is the world's best-performing open-source Arabic language model. And in English, it performs as well as LLaMa 13B despite using a fraction of the training data and a fraction of the electricity to train. Contact us to learn more: http://
cerebras.net/contact-us -
AutoTrain DreamBooth Now Available on Hugging Face Spaces
By
–
AutoTrain DreamBooth is now available for training on Hugging Face Spaces! It means, you can train models like SDXL, Stable Diffusion 1.5/2.0, etc on your own images on Spaces Hardware! Not only that, you can train multiple jobs for one model with different parameters,
-
DINOv2 Released Under Apache 2.0 License with Dense Prediction Models
By
–
To support innovation in computer vision, we’re making DINOv2 available under the Apache 2.0 license + releasing a collection of DINOv2-based dense prediction models for semantic image segmentation and monocular depth estimation.
— AI at Meta (@AIatMeta) 31 août 2023
Try our updated demo ➡️ https://t.co/ctwiBFWS4W pic.twitter.com/5tKU1JDSbWTo support innovation in computer vision, we’re making DINOv2 available under the Apache 2.0 license + releasing a collection of DINOv2-based dense prediction models for semantic image segmentation and monocular depth estimation. Try our updated demo https://
bit.ly/44FsfIQ -
DINOv2 License Expansion and FACET Benchmark for Vision Fairness
By
–
Today we’re announcing two new updates in our computer vision work — a new, expanded license for our DINOv2 model and the release of FACET, a comprehensive new benchmark dataset to help evaluate and improve fairness in vision models.
— AI at Meta (@AIatMeta) 31 août 2023
More details ➡️ https://t.co/fDHYNpGrta
🧵 pic.twitter.com/dOXDWOLKSYToday we’re announcing two new updates in our computer vision work — a new, expanded license for our DINOv2 model and the release of FACET, a comprehensive new benchmark dataset to help evaluate and improve fairness in vision models. More details https://
bit.ly/3L35E1U -
LIMA Dataset Support Added to Lit-GPT Framework
By
–
Finally got around adding LIMA to Lit-GPT (upon popular request). You can use it now to finetune any of the supported LLMs (Llama 2, Falcon, LongChat, … you name it). More usage info here: https://
github.com/Lightning-AI/l
it-gpt/blob/main/tutorials/prepare_dataset.md#lima
…